Astra can read and write weights to improve Qwen

Re:Astra can read and write weights to improve Qwen by magimas on Tuesday November 03, 2026 @03:52AM (#50349617)

are there some review papers you would recommend to get an overview over weight space interpretability research?

(can be as maths heavy as possible/necessary to understand the topic)

[ Parent | on HN ]

Re:Astra can read and write weights to improve Qwen by yurimo on Tuesday November 03, 2026 @05:12AM (#50350096)

It depends on your interest, since even though it is a subfield it is diverse. Relevant to this work here is a general overview: https://arxiv.org/abs/2603.10090

Also check out Tracr: https://deepmind.google/research/publications/22295/ Here they attempt to compile static programs into weights.

This is less of an overview but I remember reading this before, from the larger collection of posts: https://sidn.baulab.info/david_atkinson_project/

[ Parent | on HN ]