© 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 · 30063 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
15-RESID-POST-AA
30063

INDEX

Explanations

high

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

.images

-0.07

结

-0.07

整形

-0.07

Aggregate

-0.07

 sweetness

-0.07

cpt

-0.06

illet

-0.06

나

-0.06

Ft

-0.06

Picture

-0.06

POSITIVE LOGITS

 high

0.10

高

0.08

yh

0.08

 High

0.08

นอกจาก

0.07

typeorm

0.07

โรง

0.07

High

0.07

wä

0.07

 Shops

0.07

Activations Density 0.127%

No Known Activations