# Steering and interpreting LLM reasoning

Area: [Mechanistic interpretability](https://mlsanity.com/mechinterp/index.md). HTML: https://mlsanity.com/mechinterp/steering-and-interpreting-llm-reasoning/

## Key facts

- Steering and interpreting LLM reasoning: 102 papers on arXiv since 2023 (data through 14 Oct 2026).
- 9 of its 102 mapped papers (9%) cite “I Have Covered All the Bases Here: Interpreting Reasoning Features in Large Language Models via Sparse Autoencoders” (2025, arXiv 2503.18878).
- 9 of its 102 mapped papers (9%) cite “Understanding Reasoning in Thinking Language Models via Steering Vectors” (2025, arXiv 2506.18167).
- 5 new papers 24 Sep–14 Oct.

## Most cited here

- [I Have Covered All the Bases Here: Interpreting Reasoning Features in Large Language Models via Sparse Autoencoders](https://mlsanity.com/paper/2503.18878/) (2025), cited by 9 papers here
- [Understanding Reasoning in Thinking Language Models via Steering Vectors](https://mlsanity.com/paper/2506.18167/) (2025), cited by 9 papers here
- [SEAL: Steerable Reasoning Calibration of Large Language Models for Free](https://mlsanity.com/paper/2504.07986/) (2025), cited by 8 papers here
- [How does Chain of Thought Think? Mechanistic Interpretability of Chain-of-Thought Reasoning with Sparse Autoencoding](https://mlsanity.com/paper/2507.22928/) (2025), cited by 7 papers here
- [Unlocking General Long Chain-of-Thought Reasoning Capabilities of Large Language Models via Representation Engineering](https://mlsanity.com/paper/2503.11314/) (2025), cited by 6 papers here
- [Feature Extraction and Steering for Enhanced Chain-of-Thought Reasoning in Language Models](https://mlsanity.com/paper/2505.15634/) (2025), cited by 5 papers here
- [Improving Reasoning Performance in Large Language Models via Representation Engineering](https://mlsanity.com/paper/2504.19483/) (2025), cited by 4 papers here
- [Fantastic Reasoning Behaviors and Where to Find Them: Unsupervised Discovery of the Reasoning Process](https://mlsanity.com/paper/2512.23988/) (2025), cited by 3 papers here
- [Controllable LLM Reasoning via Sparse Autoencoder-Based Steering](https://mlsanity.com/paper/2601.03595/) (2026), cited by 3 papers here
- [Reasoning Circuits in Language Models: A Mechanistic Interpretation of Syllogistic Inference](https://mlsanity.com/paper/2408.08590/) (2024), cited by 2 papers here

## New (24 Sep–14 Oct)

- [MAPLE: A Multi-Axis Parametric Knowledge Extraction Lens for LLM Evaluation](https://mlsanity.com/paper/2610.19827/) (2026-10-14)
- [Learning to Decide, Not to Reason: Parameter-Efficient Decision Operators via Low-Rank Activation Steering](https://mlsanity.com/paper/2610.06950/) (2026-10-03)
- [Concept Subspaces Compute Beyond the Logit Lens: A Weights-Only Test for Locating Representations Upstream of Readout](https://mlsanity.com/paper/2609.39263/) (2026-09-30)
- [RESCUE: Repairing Language Model Errors to Sparse Circuits via Reinforcement Learning](https://mlsanity.com/paper/2609.36813/) (2026-09-29)
- [Understanding On-Policy Distillation: A Mechanistic Interpretability Perspective via Sparse Crosscoders](https://mlsanity.com/paper/2609.35210/) (2026-09-28)