© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals ExportsAPI Community Blog Privacy & Terms Contact

QWEN2.5-7B-IT · 11-RESID-POST-AA · 85594 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
11-RESID-POST-AA
85594

INDEX

Explanations

process

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

 начина

-0.07

<Location

-0.07

 PageInfo

-0.07

去哪里

-0.07

绝对是

-0.07

 Yönetim

-0.07

==>

-0.07

 Duplicate

-0.06

coop

-0.06

 dissolve

-0.06

POSITIVE LOGITS

_ped

0.07

esian

0.07

0.07

 fabric

0.07

igned

0.07

㊞

0.06

_pred

0.06

 eBook

0.06

ơ

0.06

 explained

0.06

Activations Density 0.003%

No Known Activations