
The first post of this series defining "auto-weight space programming" is out. We SFT Qwen3.5-4B and other models to apply logit lens on raw weights passed as numbers in the prompt, achieving 99.8% accuracy 🧵 atharva-naik.github.io/blog/…
I'm working on something a little different from what I've seen most researchers do: a blog series going deep into training small models (e.g., Qwen3.5-4B) to improve their own weight-space programming capabilities. The first post drops this Friday 🧵









