© 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 · 15-RESID-POST-AA · 16527 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
15-RESID-POST-AA
16527

INDEX

Explanations

online data processing

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_15/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.15.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

ـ

-0.07

.getInfo

-0.07

 QVector

-0.07

漴

-0.07

均由

-0.06

Charge

-0.06

ToolTip

-0.06

두

-0.06

stant

-0.06

帔

-0.06

POSITIVE LOGITS

 redirects

0.06

ybrid

0.06

.gs

0.06

 mojo

0.06

叔叔

0.06

 בת

0.06

<message

0.06

 radix

0.06

מצ

0.06

 fibers

0.06

Activations Density 0.185%

No Known Activations