A personal to-read list of papers and dissertations. I add new entries here as I come across things I want to read.

• Mechanistic Interpretability and Control for Language Models
  PhD Dissertation · Zhengxuan Wu · Stanford, 2026
• Mechanistic Data Attribution: Tracing the Training Origins of Interpretable LLM Units
  arXiv 2601.21996 · Jianhui Chen, Yuzhang Luo, Liangming Pan
• Assessing skeptical views of interpretability research
  Blog post · Christopher Potts