Skip to content

Author

Zhicheng Guo

1 paper indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Aug 2026

Scaling Inherently Interpretable Language Models

Steerling-8B remains competitive with open peer models trained on substantially 2-16x more compute, suggesting a different scaling paradigm: interpretability can be designed into training, and it improves with scale.

Guide Labs Team, Andreas Madsen, A. Ismail et al. · 3 citations · ⚡1