© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals ExportsAPI Community Blog Privacy & Terms Contact

OLMO-3-1125-32B · 32-RES-BATCHTOPK-131K · 27651 ｜ Neuronpedia

Home
Olmo-3-1125-32B
32-RES-BATCHTOPK-131K
27651

INDEX

Explanations

shocked at the

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

cer

-0.11

oli

-0.11

 tritur

-0.11

uator

-0.10

imest

-0.10

VAS

-0.10

oti

-0.10

vary

-0.10

 Inspir

-0.10

-0.10

POSITIVE LOGITS

 having

0.14

 being

0.12

how

0.11

anela

0.10

 what

0.09

having

0.09

ml

0.09

 apparent

0.08

 suddenly

0.08

odel

0.08

Activations Density 0.012%

No Known Activations