© 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 · 15-RESID-POST-AA · 114390 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
15-RESID-POST-AA
114390

INDEX

Explanations

Math papers

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

博彩

-0.07

 Garrett

-0.07

 мн

-0.07

 Crunch

-0.07

-0.07

镦

-0.07

ễn

-0.06

 milhões

-0.06

⎼

-0.06

-based

-0.06

POSITIVE LOGITS

='".$_

0.08

毗

0.08

 Registers

0.08

警方

0.07

 Criterion

0.07

(players

0.07

_instances

0.07

 getInt

0.07

ANNEL

0.07

 notify

0.07

Activations Density 0.044%

No Known Activations