ProjectAIResearch

Quantization × Interpretability | what quantization does to sparse autoencoders

Jan 2026

How model quantization affects sparse autoencoders.

What I Built

  • Sparse autoencoders trained on Qwen3-30B and StarCoder2-15B at four precisions, then compared across them.
  • Code generation breaks at INT4 while knowledge retrieval holds. Undercomplete SAEs transfer better than overcomplete ones.

Stats

168SAEs trained
99%sample correlation across precisions, BF16 to INT4
−50%code generation at INT4
2.3×better transfer for undercomplete SAEs

The Stack

ToolsPython, PyTorch, SAELens, bitsandbytes, Transformers