© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals Exports interp-engineNEWAPI Community Blog Privacy & Terms Contact

OLMO-3-1025-7B · 16-RES-MATRYOSHKA-65K · 3931 ｜ Neuronpedia

Home
Olmo-3-1025-7B
16-RES-MATRYOSHKA-65K
3931

INDEX

Explanations

:: or ->

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

yl

-0.10

ema

-0.09

vl

-0.08

ferences

-0.08

 fragile

-0.08

noinspection

-0.08

utches

-0.08

fff

-0.08

IFE

-0.08

 rout

-0.08

POSITIVE LOGITS

->

0.11

::

0.10

Ã©ric

0.10

hab

0.08

Fa

0.08

.ng

0.08

tos

0.08

 bian

0.08

 atmos

0.08

ATO

0.08

Activations Density 0.064%

No Known Activations