© 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 · 11-RESID-POST-AA · 112661 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
11-RESID-POST-AA
112661

INDEX

Explanations

Fl

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_11/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.11.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

覆盖

-0.08

 hồ

-0.07

zech

-0.07

 agree

-0.07

RowIndex

-0.07

 история

-0.07

涵盖

-0.07

≃

-0.07

-vers

-0.07

Sunday

-0.07

POSITIVE LOGITS

流产

0.08

 showModal

0.08

干活

0.07

 lightweight

0.07

 flap

0.07

 sağlam

0.07

YW

0.07

(eval

0.07

 הבריאות

0.07

小额贷款

0.07

Activations Density 0.035%

No Known Activations