© 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 · 9756 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
7-RESID-POST-AA
9756

INDEX

Explanations

intrigued

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

吞噬

-0.06

-cont

-0.06

acet

-0.06

 Composition

-0.06

_combined

-0.06

@PostMapping

-0.06

 większe

-0.06

⚖

-0.06

 kısmı

-0.06

 aşk

-0.06

POSITIVE LOGITS

 intrigued

0.08

ceived

0.07

strategy

0.07

感官

0.06

�

0.06

_CS

0.06

_CR

0.06

>(()

0.06

人工智能

0.06

坉

0.06

Activations Density 0.005%

No Known Activations