© 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 · 97304 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
11-RESID-POST-AA
97304

INDEX

Explanations

penalties

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

 Childhood

-0.07

 Stat

-0.07

赐

-0.07

宇宙

-0.07

kod

-0.07

-↵

-0.07

 Katz

-0.07

/out

-0.07

etadata

-0.07

塾

-0.07

POSITIVE LOGITS

 odby

0.07

#,

0.07

<Vector

0.07

ࠓ

0.07

🕖

0.06

 extends

0.06

🛐

0.06

.Endpoint

0.06

 clauses

0.06

 Cycle

0.06

Activations Density 0.023%

No Known Activations