© 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 · 67755 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
11-RESID-POST-AA
67755

INDEX

Explanations

Domain extensions

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

 After

-0.08

�

-0.07

☦

-0.07

喑

-0.06

ensed

-0.06

after

-0.06

:{↵

-0.06

leave

-0.06

比赛

-0.06

EF

-0.06

POSITIVE LOGITS

 לפעמים

0.07

Uh

0.07

_numbers

0.07

 dotted

0.07

 straightforward

0.07

 igen

0.07

 Earl

0.07

 nearer

0.06

muy

0.06

 Cunningham

0.06

Activations Density 0.004%

No Known Activations