© 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 · 5287 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
11-RESID-POST-AA
5287

INDEX

Explanations

to

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

_Add

-0.08

详细了解

-0.07

ак

-0.07

someone

-0.07

 amount

-0.07

(register

-0.07

𬣡

-0.07

㋯

-0.06

 instructed

-0.06

ensor

-0.06

POSITIVE LOGITS

 brutal

0.07

バリ

0.07

roy

0.07

喳

0.07

CONN

0.07

-faced

0.07

_RADIO

0.07

villa

0.07

シー

0.07

::::

0.07

Activations Density 0.015%

No Known Activations