# Mechanistic interpretability

1,591 papers in 13 research directions. Data through 14 Oct 2026.
HTML: https://mlsanity.com/mechinterp/

## Directions (largest first)

- [Circuits and mechanistic analysis](https://mlsanity.com/mechinterp/circuits-and-mechanistic-analysis/index.md): 272 papers, 1 new this week
- [Activation steering methods](https://mlsanity.com/mechinterp/activation-steering-methods/index.md): 239 papers, 5 new this week
- [SAE features and their applications](https://mlsanity.com/mechinterp/sae-features-and-their-applications/index.md): 231 papers, 4 new this week
- [Sparse autoencoder training and evaluation](https://mlsanity.com/mechinterp/sparse-autoencoder-training-and-evaluation/index.md): 175 papers, 4 new this week
- [Knowledge and representations inside LLMs](https://mlsanity.com/mechinterp/knowledge-and-representations-inside-llms/index.md): 136 papers, 0 new this week
- [Steering and probing for LLM safety](https://mlsanity.com/mechinterp/steering-and-probing-for-llm-safety/index.md): 119 papers, 0 new this week
- [Interpreting vision and multimodal models](https://mlsanity.com/mechinterp/interpreting-vision-and-multimodal-models/index.md): 105 papers, 0 new this week
- [Steering and interpreting LLM reasoning](https://mlsanity.com/mechinterp/steering-and-interpreting-llm-reasoning/index.md): 102 papers, 1 new this week
- [Probing deception, bias and beliefs](https://mlsanity.com/mechinterp/probing-deception-bias-and-beliefs/index.md): 88 papers, 2 new this week
- [Interpreting biomedical and science models](https://mlsanity.com/mechinterp/interpreting-biomedical-and-science-models/index.md): 60 papers, 0 new this week
- [Interpreting and steering diffusion models](https://mlsanity.com/mechinterp/interpreting-and-steering-diffusion-models/index.md): 27 papers, 0 new this week
- [Hallucination detection from model internals](https://mlsanity.com/mechinterp/hallucination-detection-from-model-internals/index.md): 23 papers, 1 new this week
- [Interpreting time-series and weather models](https://mlsanity.com/mechinterp/interpreting-time-series-and-weather-models/index.md): 14 papers, 0 new this week