© 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 · 7-RESID-POST-AA · 38413 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
7-RESID-POST-AA
38413

INDEX

Explanations

ums

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

当即

-0.07

 Ital

-0.07

 Brave

-0.07

倔

-0.07

ButtonClick

-0.07

Conversation

-0.07

.history

-0.06

这时

-0.06

 İki

-0.06

这家公司

-0.06

POSITIVE LOGITS

 park

0.07

膠

0.07

澹

0.07

.WriteLine

0.07

岞

0.07

act

0.07

meld

0.07

 plastic

0.06

pięt

0.06

🧊

0.06

Activations Density 0.144%

No Known Activations