{"topic":{"slug":"interpretability","name":"Mechanistic Interpretability","domain":"ai","description":"Reverse-engineering neural networks: superposition, sparse autoencoders and transcoders, circuits and attribution graphs, probing and activation steering.","keywords":["mechanistic interpretability","sparse autoencoder","superposition","circuits","activation steering","probing","attribution graph","feature visualization"],"paper_count":234,"latest_published":"2026-10-28","url":"https://space-kitty.com/topics/interpretability","api_url":"https://space-kitty.com/api/v1/topics/interpretability"},"dossier":null,"top_papers":[{"id":"doi:10.1038/nrg3934","kind":"review","title":"Systems biology and gene networks in neurodevelopmental and neurodegenerative disorders","authors":["Neelroop Parikshak","Michael J. Gandal","Daniel H. Geschwind"],"author_count":3,"year":2015,"published":"2015-07-07","venue":"Nature Reviews Genetics","cited_by":447,"doi":"10.1038/nrg3934","arxiv_id":null,"nct_id":null,"source_url":"https://doi.org/10.1038/nrg3934","archive_url":"https://space-kitty.com/papers/doi:10.1038/nrg3934"},{"id":"doi:10.1038/s41592-019-0576-7","kind":"article","title":"Exploring single-cell data with deep multitasking neural networks","authors":["Matthew Amodio","David van Dijk","Krishnan Srinivasan","William S. Chen","Hussein Mohsen","Kevin R. Moon"],"author_count":16,"year":2019,"published":"2019-10-07","venue":"Nature Methods","cited_by":297,"doi":"10.1038/s41592-019-0576-7","arxiv_id":null,"nct_id":null,"source_url":"https://doi.org/10.1038/s41592-019-0576-7","archive_url":"https://space-kitty.com/papers/doi:10.1038/s41592-019-0576-7"},{"id":"doi:10.1126/science.aam5887","kind":"article","title":"Decoding of position in the developing neural tube from antiparallel morphogen gradients","authors":["Marcin Zagórski","Yoji Tabata","Nathalie Brandenberg","Matthias P. Lütolf","Gašper Tkačik","Tobias Bollenbach"],"author_count":8,"year":2017,"published":"2017-06-30","venue":"Science","cited_by":184,"doi":"10.1126/science.aam5887","arxiv_id":null,"nct_id":null,"source_url":"https://doi.org/10.1126/science.aam5887","archive_url":"https://space-kitty.com/papers/doi:10.1126/science.aam5887"},{"id":"arxiv:2005.13073","kind":"article","title":"Biologically-informed neural networks guide mechanistic modeling from sparse experimental data","authors":["John H. Lagergren","John T. Nardini","Ruth E. Baker","Matthew J. Simpson","Kevin Flores"],"author_count":5,"year":2020,"published":"2020-12-01","venue":"PLoS Computational Biology","cited_by":167,"doi":"10.1371/journal.pcbi.1008462","arxiv_id":"2005.13073","nct_id":null,"source_url":"https://doi.org/10.1371/journal.pcbi.1008462","archive_url":"https://space-kitty.com/papers/arxiv:2005.13073"},{"id":"doi:10.1186/s13059-020-02100-5","kind":"article","title":"Knowledge-primed neural networks enable biologically interpretable deep learning on single-cell sequencing data","authors":["Nikolaus Fortelny","Christoph Bock"],"author_count":2,"year":2020,"published":"2020-08-03","venue":"Genome biology","cited_by":135,"doi":"10.1186/s13059-020-02100-5","arxiv_id":null,"nct_id":null,"source_url":"https://doi.org/10.1186/s13059-020-02100-5","archive_url":"https://space-kitty.com/papers/doi:10.1186/s13059-020-02100-5"},{"id":"doi:10.1016/j.watres.2023.120667","kind":"article","title":"Machine learning for modeling N2O emissions from wastewater treatment plants: Aligning model performance, complexity, and interpretability","authors":["Mostafa Khalil","Ahmed AlSayed","Yang Liu","Peter A. Vanrolleghem"],"author_count":4,"year":2023,"published":"2023-09-24","venue":"Water Research","cited_by":116,"doi":"10.1016/j.watres.2023.120667","arxiv_id":null,"nct_id":null,"source_url":"https://doi.org/10.1016/j.watres.2023.120667","archive_url":"https://space-kitty.com/papers/doi:10.1016/j.watres.2023.120667"},{"id":"doi:10.5194/hess-26-5085-2022","kind":"article","title":"Improving hydrologic models for predictions and process understanding using neural ODEs","authors":["Marvin Höge","Andreas Scheidegger","Marco Baity‐Jesi","Carlo Albert","Fabrizio Fenicia"],"author_count":5,"year":2022,"published":"2022-10-11","venue":"Hydrology and earth system sciences","cited_by":126,"doi":"10.5194/hess-26-5085-2022","arxiv_id":null,"nct_id":null,"source_url":"https://doi.org/10.5194/hess-26-5085-2022","archive_url":"https://space-kitty.com/papers/doi:10.5194/hess-26-5085-2022"},{"id":"doi:10.1016/j.conbuildmat.2018.09.087","kind":"article","title":"Improving accuracy of rutting prediction for mechanistic-empirical pavement design guide with deep neural networks","authors":["Hongren Gong","Yiren Sun","Zijun Mei","Baoshan Huang"],"author_count":4,"year":2018,"published":"2018-09-28","venue":"Construction and Building Materials","cited_by":130,"doi":"10.1016/j.conbuildmat.2018.09.087","arxiv_id":null,"nct_id":null,"source_url":"https://doi.org/10.1016/j.conbuildmat.2018.09.087","archive_url":"https://space-kitty.com/papers/doi:10.1016/j.conbuildmat.2018.09.087"},{"id":"arxiv:2310.19998","kind":"article","title":"Generative Retrieval-Augmented Ontologic Graph and Multiagent Strategies for Interpretive Large Language Model-Based Materials Design","authors":["Markus J. Buehler"],"author_count":1,"year":2024,"published":"2024-01-12","venue":"ACS Engineering Au","cited_by":82,"doi":"10.1021/acsengineeringau.3c00058","arxiv_id":"2310.19998","nct_id":null,"source_url":"https://doi.org/10.1021/acsengineeringau.3c00058","archive_url":"https://space-kitty.com/papers/arxiv:2310.19998"},{"id":"doi:10.1016/j.devcel.2012.09.015","kind":"article","title":"Mechanistic Differences in the Transcriptional Interpretation of Local and Long-Range Shh Morphogen Signaling","authors":["Tony Oosterveen","Sanja Kurdija","Zhanna Alekseenko","Christopher W. Uhde","Maria Bergsland","Magnus Sandberg"],"author_count":10,"year":2012,"published":"2012-11-01","venue":"Developmental Cell","cited_by":132,"doi":"10.1016/j.devcel.2012.09.015","arxiv_id":null,"nct_id":null,"source_url":"https://doi.org/10.1016/j.devcel.2012.09.015","archive_url":"https://space-kitty.com/papers/doi:10.1016/j.devcel.2012.09.015"},{"id":"doi:10.1371/journal.pcbi.1008472","kind":"article","title":"Development of a hybrid model for a partially known intracellular signaling pathway through correction term estimation and neural network modeling","authors":["Dongheon Lee","Arul Jayaraman","Joseph Sang‐Il Kwon"],"author_count":3,"year":2020,"published":"2020-12-14","venue":"PLoS Computational Biology","cited_by":103,"doi":"10.1371/journal.pcbi.1008472","arxiv_id":null,"nct_id":null,"source_url":"https://doi.org/10.1371/journal.pcbi.1008472","archive_url":"https://space-kitty.com/papers/doi:10.1371/journal.pcbi.1008472"},{"id":"doi:10.3389/fimmu.2024.1363144","kind":"review","title":"A review of mechanistic learning in mathematical oncology","authors":["John Metzcar","Catherine Ruth Jutzeler","Paul Macklin","Alvaro Köhn‐Luque","Sarah C. Brüningk"],"author_count":5,"year":2024,"published":"2024-03-12","venue":"Frontiers in Immunology","cited_by":70,"doi":"10.3389/fimmu.2024.1363144","arxiv_id":null,"nct_id":null,"source_url":"https://doi.org/10.3389/fimmu.2024.1363144","archive_url":"https://space-kitty.com/papers/doi:10.3389/fimmu.2024.1363144"},{"id":"doi:10.1126/sciadv.aax5979","kind":"article","title":"Efficient inverse graphics in biological face processing","authors":["Ilker Yildirim","Mario Belledonne","Winrich A. Freiwald","Joshua B. Tenenbaum"],"author_count":4,"year":2020,"published":"2020-03-04","venue":"Science Advances","cited_by":89,"doi":"10.1126/sciadv.aax5979","arxiv_id":null,"nct_id":null,"source_url":"https://doi.org/10.1126/sciadv.aax5979","archive_url":"https://space-kitty.com/papers/doi:10.1126/sciadv.aax5979"},{"id":"doi:10.3389/fnins.2022.906290","kind":"review","title":"Explainable AI: A review of applications to neuroimaging data","authors":["Farzad V. Farahani","Krzysztof Fiok","Behshad Lahijanian","Waldemar Karwowski","Pamela K. Douglas"],"author_count":5,"year":2022,"published":"2022-12-01","venue":"Frontiers in Neuroscience","cited_by":81,"doi":"10.3389/fnins.2022.906290","arxiv_id":null,"nct_id":null,"source_url":"https://doi.org/10.3389/fnins.2022.906290","archive_url":"https://space-kitty.com/papers/doi:10.3389/fnins.2022.906290"},{"id":"doi:10.14573/altex.2309191","kind":"article","title":"ToxAIcology - The evolving role of artificial intelligence in advancing toxicology and modernizing regulatory science","authors":["Thomas Härtung"],"author_count":1,"year":2023,"published":"2023-01-01","venue":"ALTEX","cited_by":77,"doi":"10.14573/altex.2309191","arxiv_id":null,"nct_id":null,"source_url":"https://doi.org/10.14573/altex.2309191","archive_url":"https://space-kitty.com/papers/doi:10.14573/altex.2309191"}],"newest_papers":[{"id":"arxiv:2610.38103","kind":"preprint","title":"The Prestige: Benchmarking Cognitive Visual Reasoning using Magic Tricks","authors":["Shuo Wen","Beixi Du","Edwin Meriaux","Junming Shi","Chloe Si","David Meger"],"author_count":8,"year":2026,"published":"2026-10-28","venue":null,"cited_by":null,"doi":null,"arxiv_id":"2610.38103","nct_id":null,"source_url":"https://arxiv.org/abs/2610.38103","archive_url":"https://space-kitty.com/papers/arxiv:2610.38103"},{"id":"arxiv:2610.38169","kind":"preprint","title":"Replaying the Same Gradients at a Different $\\varepsilon$: A Registered Test of the Fixed-Trajectory Account of Adam's $\\varepsilon$ for One Rare Row","authors":["Lngel Kyo"],"author_count":1,"year":2026,"published":"2026-10-28","venue":null,"cited_by":null,"doi":null,"arxiv_id":"2610.38169","nct_id":null,"source_url":"https://arxiv.org/abs/2610.38169","archive_url":"https://space-kitty.com/papers/arxiv:2610.38169"},{"id":"arxiv:2610.38174","kind":"preprint","title":"Scaling Lean Theorem Proving for Real-World Code Verification","authors":["Debargha Ganguly","Divya Raghunathan","Dejan Jovanović","Vikash Singh","Soonho Kong","Aaron Tomb"],"author_count":9,"year":2026,"published":"2026-10-28","venue":null,"cited_by":null,"doi":null,"arxiv_id":"2610.38174","nct_id":null,"source_url":"https://arxiv.org/abs/2610.38174","archive_url":"https://space-kitty.com/papers/arxiv:2610.38174"},{"id":"arxiv:2610.38193","kind":"preprint","title":"Barren Plateaus in Quantum Linear Combinations: Interference and Lie-Algebraic Control","authors":["Amir Koutahi","Pouya Kananian","Hans-Arno Jacobsen"],"author_count":3,"year":2026,"published":"2026-10-28","venue":null,"cited_by":null,"doi":null,"arxiv_id":"2610.38193","nct_id":null,"source_url":"https://arxiv.org/abs/2610.38193","archive_url":"https://space-kitty.com/papers/arxiv:2610.38193"},{"id":"arxiv:2610.38201","kind":"preprint","title":"From Natural Language to Real Schematics: An Automated Workflow for Power Electronics Schematic Synthesis","authors":["Bowen Su","Huan Chen","Jiahua Ying","Ran Ou","Weilong Chen","Li Xue"],"author_count":7,"year":2026,"published":"2026-10-28","venue":null,"cited_by":null,"doi":null,"arxiv_id":"2610.38201","nct_id":null,"source_url":"https://arxiv.org/abs/2610.38201","archive_url":"https://space-kitty.com/papers/arxiv:2610.38201"},{"id":"arxiv:2610.38312","kind":"preprint","title":"Robust LLM-Generated Text Detection through Matched Conditional-Response Probing","authors":["Junfeng Hao","Wenxian Wang","Tao Leng","Xingshu Chen","Hao Ren","Haizhou Wang"],"author_count":6,"year":2026,"published":"2026-10-28","venue":null,"cited_by":null,"doi":null,"arxiv_id":"2610.38312","nct_id":null,"source_url":"https://arxiv.org/abs/2610.38312","archive_url":"https://space-kitty.com/papers/arxiv:2610.38312"},{"id":"arxiv:2610.38326","kind":"preprint","title":"Can LLMs Faithfully Solve Ontology Engineering Tasks? A Mechanistic Interpretability Study","authors":["Bohui Zhang","Albert Meroño-Peñuela","Elena Simperl"],"author_count":3,"year":2026,"published":"2026-10-28","venue":null,"cited_by":null,"doi":null,"arxiv_id":"2610.38326","nct_id":null,"source_url":"https://arxiv.org/abs/2610.38326","archive_url":"https://space-kitty.com/papers/arxiv:2610.38326"},{"id":"arxiv:2610.38405","kind":"preprint","title":"SpaceAct: Benchmarking 3D Spatial and Temporal Reasoning via Closed-Loop Action and Active Perception","authors":["Chenglong Shi","Zekai Yuan","Yue Song","Jon Pu","Will Wu"],"author_count":5,"year":2026,"published":"2026-10-28","venue":null,"cited_by":null,"doi":null,"arxiv_id":"2610.38405","nct_id":null,"source_url":"https://arxiv.org/abs/2610.38405","archive_url":"https://space-kitty.com/papers/arxiv:2610.38405"},{"id":"arxiv:2610.38520","kind":"preprint","title":"What Hallucinations Have We Measured? Semantic Illusion, Confabulation, and Expressed Uncertainty","authors":["Hazel H. Kim","Jakub Binkowski","Ekaterina Fadeeva","Juan David Guerra","Yijie Hao","Zheng Yi Ho"],"author_count":25,"year":2026,"published":"2026-10-28","venue":null,"cited_by":null,"doi":null,"arxiv_id":"2610.38520","nct_id":null,"source_url":"https://arxiv.org/abs/2610.38520","archive_url":"https://space-kitty.com/papers/arxiv:2610.38520"},{"id":"arxiv:2610.38526","kind":"preprint","title":"Value Probes: Learned Value Functions for Beam-Search Red Teaming","authors":["Jonathan F. Jao","Andrew Kyle Lampinen"],"author_count":2,"year":2026,"published":"2026-10-28","venue":null,"cited_by":null,"doi":null,"arxiv_id":"2610.38526","nct_id":null,"source_url":"https://arxiv.org/abs/2610.38526","archive_url":"https://space-kitty.com/papers/arxiv:2610.38526"}],"related_topics":[{"slug":"llm-architectures","name":"LLM Architectures & Pretraining","api_url":"https://space-kitty.com/api/v1/topics/llm-architectures"},{"slug":"scaling-laws","name":"Scaling Laws & Compute-Optimal Training","api_url":"https://space-kitty.com/api/v1/topics/scaling-laws"},{"slug":"reasoning-models","name":"Reasoning Models & Test-Time Compute","api_url":"https://space-kitty.com/api/v1/topics/reasoning-models"},{"slug":"alignment-safety","name":"AI Alignment & Safety","api_url":"https://space-kitty.com/api/v1/topics/alignment-safety"},{"slug":"ai-agents","name":"LLM Agents & Tool Use","api_url":"https://space-kitty.com/api/v1/topics/ai-agents"},{"slug":"generative-multimodal","name":"Generative & Multimodal Models","api_url":"https://space-kitty.com/api/v1/topics/generative-multimodal"},{"slug":"efficient-ai","name":"Efficient Training & Inference","api_url":"https://space-kitty.com/api/v1/topics/efficient-ai"},{"slug":"ai-for-science","name":"AI for Science","api_url":"https://space-kitty.com/api/v1/topics/ai-for-science"},{"slug":"robotics-embodied","name":"Robot Learning & Embodied AI","api_url":"https://space-kitty.com/api/v1/topics/robotics-embodied"}],"premium":{"dossier":null,"research_pack":{"url":"https://space-kitty.com/api/v1/topics/interpretability/pack","price_usd":"0.20"}},"more":"https://space-kitty.com/api/v1/topics/interpretability/papers?sort=top&limit=100"}