attentionmech/tensorlens

aesthetic tensor visualiser

29
/ 100
Experimental

TensorLens helps machine learning practitioners visually inspect the internal workings of their models. It takes in numerical data representing model weights, activations, or other tensor data, and outputs an interactive visual representation. This tool is ideal for researchers, data scientists, and ML engineers who need to understand how their neural networks are processing information.

No commits in the last 6 months.

Use this if you need to quickly and interactively visualize 1D, 2D, or 3D numerical data within your machine learning models to debug or gain insights.

Not ideal if you need to visualize tensors with more than three dimensions or require highly specialized, domain-specific visualization techniques.

machine-learning-debugging neural-network-analysis model-interpretability deep-learning-research tensor-inspection
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 4 / 25

How are scores calculated?

Stars

27

Forks

1

Language

Jupyter Notebook

License

Apache-2.0

Last pushed

Apr 23, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/attentionmech/tensorlens"

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