© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Natural Language

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

QWEN2.5-7B-IT · 11-RESID-POST-AA · 59396 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
11-RESID-POST-AA
59396

INDEX

Explanations

cleaning

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

 Screening

-0.07

/apt

-0.07

'])

-0.06

_TAC

-0.06

赛后

-0.06

(exec

-0.06

 Disclosure

-0.06

cdot

-0.06

_CLIP

-0.06

独立董事

-0.06

POSITIVE LOGITS

стр

0.07

ingt

0.07

 family

0.07

汹

0.06

₁

0.06

 Dungeon

0.06

elves

0.06

 إي

0.06

icolor

0.06

 gương

0.06

Activations Density 0.082%

No Known Activations