© 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 · 26828 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
11-RESID-POST-AA
26828

INDEX

Explanations

Code

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

 participates

-0.06

ᗪ

-0.06

 misunderstand

-0.06

gc

-0.06

iek

-0.06

aneously

-0.06

Tow

-0.06

raw

-0.06

 persever

-0.06

 Infrastructure

-0.06

POSITIVE LOGITS

 straps

0.08

散户

0.07

currentTime

0.07

不如

0.07

４

0.07

ﬤ

0.07

２

0.07

公元

0.07

赶到

0.06

NotEmpty

0.06

Activations Density 0.000%

No Known Activations