© 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 · 15-RESID-POST-AA · 48196 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
15-RESID-POST-AA
48196

INDEX

Explanations

integrate

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_15/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.15.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

声响

-0.08

聩

-0.07

 Aston

-0.07

(?:

-0.07

נזק

-0.07

чь

-0.07

שות

-0.07

չ

-0.07

恹

-0.07

recur

-0.06

POSITIVE LOGITS

 integration

0.09

integration

0.07

 integr

0.07

_im

0.07

 Integrated

0.07

 Integration

0.07

化的

0.06

.linalg

0.06

ibr

0.06

 integrated

0.06

Activations Density 0.026%

No Known Activations