© 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

QWEN2.5-7B-IT · 15-RESID-POST-AA · 119401 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
15-RESID-POST-AA
119401

INDEX

Explanations

Period

np_max-act · gemini-2.0-flash

New Auto-Interp

Top Features by Cosine Similarity

Configuration

andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.15.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

Show PlotsShow ExplanationShow ActivationsShow Test FieldShow SteerShow Link

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

巽

-0.07

_resp

-0.07

 competency

-0.06

宠

-0.06

.hr

-0.06

 ее

-0.06

 erotiske

-0.06

 miser

-0.06

罐

-0.06

 deren

-0.06

POSITIVE LOGITS

ۓ

0.07

ctest

0.07

 artykuł

0.07

 DataColumn

0.07

<View

0.06

콴

0.06

ようです

0.06

FORMAT

0.06

いません

0.06

*}

0.06

Activations Density 0.006%

No Known Activations