© 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 · 77359 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
11-RESID-POST-AA
77359

INDEX

Explanations

@

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

 kaynağı

-0.07

ApiOperation

-0.07

ano

-0.07

 Jerseys

-0.07

훍

-0.07

 Accounting

-0.07

<Entry

-0.06

 ElementType

-0.06

creenshot

-0.06

 exclusion

-0.06

POSITIVE LOGITS

Encoded

0.07

Aux

0.07

.d

0.06

植物

0.06

(ptr

0.06

表面

0.06

口服

0.06

麈

0.06

_program

0.06

كسر

0.06

Activations Density 0.004%

No Known Activations