© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Jacobian LensNEW

Natural Language

MAY 26 Assistant AxisJAN 26 Circuit TracerAPR 26Steer SAE Evals Exports interp-engineNEW Community Blog Privacy & Terms Contact

OLMO-3-1125-32B · 32-RES-BATCHTOPK-131K · 7990 ｜ Neuronpedia

Home
Olmo-3-1125-32B
32-RES-BATCHTOPK-131K
7990

INDEX

Explanations

opinion shall

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Configuration

bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

No Configuration Found

Embeds

Show PlotsShow ExplanationShow ActivationsShow Test FieldShow SteerShow Link

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Barth

-0.10

 voluntary

-0.09

anson

-0.09

essler

-0.09

NaN

-0.09

artin

-0.09

-0.09

onis

-0.09

utes

-0.08

rix

-0.08

POSITIVE LOGITS

hone

0.10

ovsky

0.09

 Crimes

0.09

 intrig

0.09

Occurred

0.09

Hen

0.09

tres

0.09

 junction

0.09

HV

0.09

 grounded

0.08

Activations Density 0.007%

No Known Activations