© 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 · 3208 ｜ Neuronpedia

Home
Olmo-3-1025-7B
16-RES-MATRYOSHKA-65K
3208

INDEX

Explanations

figure 1 shows

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

isy

-0.11

-arrow

-0.11

essa

-0.11

imonial

-0.10

ado

-0.10

byss

-0.10

ibel

-0.10

Lens

-0.10

.Transform

-0.10

/></

-0.10

POSITIVE LOGITS

reader

0.06

ONE

0.06

 late

0.06

 mature

0.06

 process

0.06

 Dictionary

0.06

 Floyd

0.06

 exagger

0.06

pe

0.06

::

0.06

Activations Density 0.039%

No Known Activations