© 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 · 7-RESID-POST-AA · 76091 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
7-RESID-POST-AA
76091

INDEX

Explanations

Banking and payments

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_7/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.7.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

ara

-0.07

/course

-0.07

_PKT

-0.07

ẽ

-0.07

DebugEnabled

-0.07

orda

-0.07

reece

-0.07

 come

-0.07

(asset

-0.07

✟

-0.07

POSITIVE LOGITS

 Wildcats

0.07

 отказ

0.07

 ballot

0.07

卫星

0.07

 accident

0.07

↵

0.07

 cambios

0.07

燹

0.06

 mari

0.06

他表示

0.06

Activations Density 0.001%

No Known Activations