XC/02 — ABOUTINDEPENDENT RESEARCHER · LLM SAFETY & INTERPRETABILITY1 PERSON

Independent research,
open by default.

Mission

Xuehang Cang is an independent researcher working on LLM safety and mechanistic interpretability. The core project, PICK, locates and surgically removes refusal behavior from language models using component-level attribution and rank-1 LoRA. Everything ships in the open — code, datasets, experiment logs, and the results that didn't work.

How I work

End-to-end ownership of the research pipeline: dataset curation (safe_prompt, unsafe_prompt), model analysis (activation patching, residual stream attribution), component ablation (KL-constrained LoRA), and evaluation (refusal rate, KL divergence, capability retention). Every experiment is logged; every finding is published. The work is the work.

AResearcherXUEHANG CANG
XC
Xuehang Cang
RESEARCHER
LLM Safety · Interpretability · Component Ablation