© 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 · 8311 ｜ Neuronpedia

Home
Olmo-3-1125-32B
32-RES-BATCHTOPK-131K
8311

INDEX

Explanations

way to

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

Negative Logits

 Worse

-0.09

ault

-0.09

 Still

-0.09

iale

-0.08

 vÃ©

-0.08

isque

-0.08

 Another

-0.08

 another

-0.08

din

-0.08

another

-0.08

POSITIVE LOGITS

 likewise

0.20

 hers

0.16

 theirs

0.13

 Likewise

0.12

dit

0.12

dit

0.11

 vice

0.11

Dit

0.10

 ours

0.10

 Overs

0.10

Activations Density 0.251%

No Known Activations