Skip to the card

2026-11-20 issue

Observed arrival · 2026-11-20

TensorLupa makes a language model’s choices visible

tensorlupa.com Visit website
Editorial interest 84/100 Selection signal · not a rating of the site

A browser-based studio lets you inspect a small language model’s token choices, probabilities, and attention as it generates text.

Landing page captured for the 2026-11-20 issue.
For
People learning how language models generate text
Worth noticing
The page reports a 100% success rate on its three-requested-words test when using a custom growing push toward unused words.

Field notes

The model is micro-Qwen3, trained from scratch on TinyStories V2 and then instruction-tuned on 900,000 TinyStoriesInstruct dialogues. The page says the browser studio uses 8-bit weights and the same C engine compiled to WebAssembly; a 4-bit build is offered for ESP32-S3 use. It reports a 100% result on its three-word instruction test with a custom growing push toward unused words, compared with 64% after instruction tuning alone.

Observed signals

Read the marks

Editorial observations of this landing page, not a rating.

○OpenPublic substance visible
✦PrettyNotable craft visible
●ProPolished or operationally mature
◎NicheUnusually specific use

One card from the complete issue

The Woven Index

386,049 arrived 1,000 judged 972 catalogued Enter the complete issue
tensorlupa.com

Landing page observed 2026-11-20. The live site may have changed.