© 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 · 11-RESID-POST-AA · 40722 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
11-RESID-POST-AA
40722

INDEX

Explanations

that

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_11/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.11.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

.shtml

-0.07

 positional

-0.07

 önemli

-0.07

.Hash

-0.07

 chút

-0.07

扩张

-0.07

_resp

-0.07

 Prep

-0.07

 withStyles

-0.06

 üzer

-0.06

POSITIVE LOGITS

CONS

0.08

 omap

0.07

𝘴

0.07

SCRIPTION

0.07

ICC

0.06

'>"

0.06

采摘

0.06

++)↵

0.06

DG

0.06

"↵↵↵

0.06

Activations Density 0.023%

No Known Activations