Randomized trial demonstrates interactive 3D visualization of language model data, indicating enhanced interpretability.
v2 corrigendum (2026-05-21): Bibliography polished to canonical forms — Bycroft (December 2023) year corrected, full author lists added for Bricken et al. (24 authors) and Carter et al. (5 authors), DOIs added for Vig (10.18653/v1/P19-3007) and Activation Atlas (10.23915/distill.00015). Self-references aligned to canonical author name. Author byline corrected from 'norika' to 'Chen, Ho Yiing'. No changes to data, viewer, or claims. This record releases Mercury-Viewer, a single HTML file (~2 MB) that opens in any browser and shows the inside of a transformer language model as a 3D point cloud. No install, no server, no GPU, no API key. Mercury-Viewer reads activation data from the Mercury sensor grid and draws it in cylindrical coordinates: azimuth is the hidden dimension index, radius is the activation quantile, height is how many prompts activated a given unit. Every point keeps a full (L, D, Q) coordinate, so hovering reveals the exact location, and the picture is invertible. Alongside the viewer, this record releases the Mercury-3B-7B observation dataset: 21,694 fired-cell records and 28,654 visible Rosen-bridge co-firing edges, captured by running ten multilingual prompts through qwen2.5:3B and qwen2.5:7B on a single RTX 3060. Code MIT, data CC-BY-4.0. Companion records: Mercury method paper (10.5281/zenodo.20312638), and forthcoming Mercury discovery and scaling preprints.
No takes yet. Share an insight, caveat, or question.
Ho Yiing Chen (2026) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: