© 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 · 109255 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
11-RESID-POST-AA
109255

INDEX

Explanations

license

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

 HRESULT

-0.07

 contar

-0.07

朗

-0.07

 completo

-0.07

CC

-0.07

⌵

-0.07

 cambio

-0.07

 matrix

-0.06

∧

-0.06

 Sparse

-0.06

POSITIVE LOGITS

:any

0.08

okable

0.08

 Business

0.07

頭

0.07

ក

0.07

license

0.07

elligence

0.07

isLoggedIn

0.07

employ

0.07

(touch

0.07

Activations Density 0.000%

No Known Activations