# Mechanistic Interpretability: State of the Field (October 2026)

Research dossier · v1 · updated 2026-10-30 · 6,205 words · 108 sources · 29 claims · verification: verified

An expert briefing on mechanistic interpretability as of late October 2026: superposition and linear features, sparse autoencoders and transcoders, automated circuit discovery and attribution graphs, causal-abstraction theory, probing, activation steering and the use of these tools in model audits. The central takeaway is that the tools now trace parts of the computation of production-scale models and appear in pre-deployment audits, yet controlled benchmarks find sparse-dictionary features often no better than neurons, linear probes or prompting on practical tasks, and the faithfulness and uniqueness of explanations remain unresolved. Work in 2026 concentrates on automating attribution-graph analysis, ground-truth testbeds and formal guarantees.

## Contents

- Executive summary
- Background and core concepts
- Timeline of key milestones
- State of the art
  - Superposition and feature geometry
  - Sparse autoencoders: scale, variants and pathologies
  - Transcoders, replacement models and attribution graphs
  - Circuit discovery and causal localization
  - Probing, latent knowledge and lenses
  - Steering and representation engineering
  - Auditing, model diffing and monitoring
  - Beyond language models
  - Interpretable-by-design models and parameter-space methods
  - Quantitative benchmarks
- Open problems and active debates
- Major programs and players
- Outlook: what to watch (November 2026 to April 2028)
- Key papers
- Glossary

## Sample findings

- Superposition remains the organizing hypothesis for polysemantic neurons: networks store more sparse features than they have dimensions and accept interference between them.
- Sparse autoencoders trained on language-model activations yield feature directions that automated methods judge more interpretable and monosemantic than directions from alternative decompositions.

## Get the full dossier

GET https://space-kitty.com/api/v1/dossiers/interpretability costs $0.20 via x402 (USDC on Base Sepolia (testnet)). Send `Accept: text/markdown` for Markdown or `application/json` for structured data (claims with citations, timeline, benchmarks, open problems, glossary, bibliography).
---
Space Kitty Archive · https://space-kitty.com · API: https://space-kitty.com/api/v1 · MCP: https://space-kitty.com/mcp · Premium: $0.20/request via x402 (Base Sepolia (testnet)). Metadata: arXiv (CC0), OpenAlex (CC0), Europe PMC (CC BY/CC0 works), ClinicalTrials.gov.