© 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 · 64711 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
11-RESID-POST-AA
64711

INDEX

Explanations

period

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

_PUSH

-0.08

 Math

-0.07

分歧

-0.07

.append

-0.07

웤

-0.07

getConfig

-0.07

<Func

-0.06

 Interested

-0.06

[]>(

-0.06

桠

-0.06

POSITIVE LOGITS

 Flame

0.07

 ↵	↵

0.07

韨

0.07

实惠

0.07

 fooled

0.07

cite

0.07

悭

0.07

脱

0.06

/.↵

0.06

 لي

0.06

Activations Density 0.001%

No Known Activations