© 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 · 75712 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
11-RESID-POST-AA
75712

INDEX

Explanations

frame

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

锚

-0.08

_tax

-0.08

 templ

-0.08

Қ

-0.07

snap

-0.07

おく

-0.07

 интер

-0.07

amb

-0.07

氮

-0.07

-centered

-0.07

POSITIVE LOGITS

.concat

0.07

 costa

0.07

遭遇

0.07

ForResource

0.06

classname

0.06

ote

0.06

 менее

0.06

SH

0.06

,System

0.06

的照片

0.06

Activations Density 0.006%

No Known Activations