© 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-3-1025-7B · 16-RES-MATRYOSHKA-65K · 1740 ｜ Neuronpedia

Home
Olmo-3-1025-7B
16-RES-MATRYOSHKA-65K
1740

INDEX

Explanations

More particularly

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

New Auto-Interp

Top Features by Cosine Similarity

Configuration

decoderesearch/olmo-3-saes/olmo-3-1025-7b

Prompts (Dashboard)

24,576 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

 more

-0.13

 most

-0.09

 much

-0.09

 MORE

-0.09

 More

-0.08

 daha

-0.08

 fewer

-0.08

 less

-0.08

 greater

-0.08

 mais

-0.07

POSITIVE LOGITS

 importantly

0.20

tti

0.16

-or

0.15

 likely

0.15

ira

0.14

ndo

0.14

au

0.14

_vert

0.13

ncy

0.13

erer

0.13

Activations Density 0.325%

No Known Activations