© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals ExportsAPI Community Blog Privacy & Terms Contact

QWEN2.5-7B-IT · 7-RESID-POST-AA · 57040 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
7-RESID-POST-AA
57040

INDEX

Explanations

Bank

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_7/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.7.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

_finish

-0.07

 inducing

-0.07

 estimating

-0.07

 Solve

-0.07

(of

-0.07

 века

-0.07

[[

-0.07

(nodes

-0.07

LS

-0.07

"For

-0.06

POSITIVE LOGITS

практи

0.08

部署

0.07

建筑面积

0.07

missions

0.07

 карт

0.06

 Cait

0.06

궨

0.06

ACEMENT

0.06

bron

0.06

 gust

0.06

Activations Density 0.002%

No Known Activations