guidelabs/steerling

Interpretable Causal Diffusion Language Models

49
/ 100
Emerging

Steerling helps AI developers and researchers generate text while also understanding why a language model makes certain predictions. It takes a text prompt as input and produces generated text, along with detailed explanations of which 'concepts' (identifiable patterns) influenced each part of the output. This allows technical users to peek inside the model's decision-making process.

195 stars. Available on PyPI.

Use this if you are a machine learning engineer or researcher who needs to generate text using a large language model and critically analyze or control the underlying factors driving its output.

Not ideal if you are looking for a simple, off-the-shelf text generation tool without needing to delve into model interpretability or have limited GPU resources.

AI-research NLP-engineering model-interpretability text-generation explainable-AI
Maintenance 10 / 25
Adoption 10 / 25
Maturity 20 / 25
Community 9 / 25

How are scores calculated?

Stars

195

Forks

9

Language

Python

License

Apache-2.0

Last pushed

Feb 23, 2026

Commits (30d)

0

Dependencies

7

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/guidelabs/steerling"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.