© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals Exports interp-engineNEWAPI Community Blog Privacy & Terms Contact

QWEN2.5-7B-IT · 7-RESID-POST-AA · 58508 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
7-RESID-POST-AA
58508

INDEX

Explanations

Names

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

爱你

-0.07

功劳

-0.07

IntPtr

-0.07

нская

-0.07

 hometown

-0.06

san

-0.06

咻

-0.06

_UnityEngine

-0.06

 whoever

-0.06

ağı

-0.06

POSITIVE LOGITS

 Private

0.07

leştir

0.07

	insert

0.07

𖧷

0.06

 differ

0.06

	NULL

0.06

 takes

0.06

ambique

0.06

可持续

0.06

 continue

0.06

Activations Density 0.014%

No Known Activations