Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models

Hengyuan Zhang, Zhihao Zhang, Mingyang Wang, Zunhai Su, Yiwei Wang +23 more
1/20/2026
cs.CL

Official code: rattlesnakey/Awesome-Actionable-MI-Survey (154 stars, MIT, last commit 2026-04-15). 1 more implementation below.

Abstract

Mechanistic Interpretability (MI) has emerged as a vital approach to demystify the opaque decision-making of Large Language Models (LLMs). However, existing reviews primarily treat MI as an observational science, summarizing analytical insights while lacking a systematic framework for actionable intervention. To bridge this gap, we present a practical survey structured around the pipeline: "Locate, Steer, and Improve." We formally categorize Localizing (diagnosis) and Steering (intervention) methods based on specific Interpretable Objects to establish a rigorous intervention protocol. Furthermore, we demonstrate how this framework enables tangible improvements in Alignment, Capability, and Efficiency, effectively operationalizing MI as an actionable methodology for model optimization. The curated paper list of this work is available at https://github.com/rattlesnakey/Awesome-Actionable-MI-Survey.

View on arXivView PDF

Code Implementations(2)

rattlesnakey/Awesome-Actionable-MI-SurveyOfficial100%
MIT

The Github repo for our survey paper: "Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models"

15413Jan 20, 20266 months agoMIT
LLM-MI-Research/Awesome-Actionable-MICommunity73%

The Github Repo for our survey paper: "Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models"

10Jan 20, 20269 months ago

Similar Papers

Mechanistic Interpretability for Large Language Model Alignment: Progress, Challenges, and Future Directions

85% match2026

Enhancing Semantic Consistency of Large Language Models through Model Editing: An Interpretability-Oriented Approach

84% match2025

Findings of the BlackboxNLP 2025 Shared Task: Localizing Circuits and Causal Variables in Language Models

84% match2025

A Practical Review of Mechanistic Interpretability for Transformer-Based Language Models

83% match1 repo2732024

A Causal Explainable Guardrails for Large Language Models

83% match2024

Activation Scaling for Steering and Interpreting Language Models

83% match1 repo22024

Cite this paper

@article{zhang2026locate,
  title  = {Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models},
  author = {Hengyuan Zhang and Zhihao Zhang and Mingyang Wang and Zunhai Su and Yiwei Wang and Qianli Wang and Shuzhou Yuan and Ercong Nie and Xufeng Duan and Qibo Xue and Zeping Yu and Chenming Shang and Xiao Liang and Jing Xiong and Hui Shen and Chaofan Tao and Zhengwu Liu and Senjie Jin and Zhiheng Xi and Dongdong Zhang and Sophia Ananiadou and Tao Gui and Ruobing Xie and Hayden Kwok-Hay So and Hinrich Schütze and Xuanjing Huang and Qi Zhang and Ngai Wong},
  year   = {2026},
  eprint = {2601.14004},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2601.14004v3}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2601.14004.svg)](https://codeofpaper.com/paper/2601.14004)

Discussion