© 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 · 2550 ｜ Neuronpedia

Home
Olmo-3-1025-7B
16-RES-MATRYOSHKA-65K
2550

INDEX

Explanations

first time in years

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

awi

-0.10

kok

-0.10

oby

-0.09

/games

-0.09

 indu

-0.09

ropa

-0.09

 Quint

-0.08

 barg

-0.08

.BASELINE

-0.08

eg

-0.08

POSITIVE LOGITS

 since

0.15

since

0.12

 seit

0.11

 rare

0.11

 reminiscent

0.10

 Rare

0.10

 depuis

0.10

 Since

0.10

Since

0.10

_since

0.10

Activations Density 0.288%

No Known Activations