© 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 · 103139 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
7-RESID-POST-AA
103139

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_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

⼦

-0.08

Ship

-0.07

 Smart

-0.07

Interactive

-0.07

set

-0.07

◦

-0.07

append

-0.07

动作

-0.07

Commercial

-0.07

",&

-0.07

POSITIVE LOGITS

yü

0.08

 BitConverter

0.07

買い

0.07

𝇠

0.07

 LogLevel

0.07

_cent

0.07

प

0.07

Türkiye

0.07

亚运会

0.07

郿

0.07

Activations Density 0.027%

No Known Activations