© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

APIAssistant AxisNEW Circuit TracerNEW Steer SAE Evals Exports Community Blog Privacy & Terms Contact

QWEN2.5-7B-IT · 19-RESID-POST-AA · 110186 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
19-RESID-POST-AA
110186

INDEX

Explanations

icals

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Top Features by Cosine Similarity

Configuration

andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.19.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

(Block

-0.07

TypeError

-0.07

👤

-0.07

*)((

-0.07

 buffs

-0.07

/linux

-0.07

 PROGMEM

-0.07

IDTH

-0.07

_camera

-0.07

ไป

-0.07

POSITIVE LOGITS

阜阳

0.08

Hat

0.07

Met

0.07

 half

0.06

set

0.06

Rates

0.06

态

0.06

二代

0.06

 realized

0.06

伟大复兴

0.06

Activations Density 0.000%

No Known Activations