INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_12.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.12.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

çĭĲ

-0.26

 examples

-0.25

tems

-0.25

ä¸ĩè±¡

-0.25

å°±æľī

-0.25

ä¸įå¦Ĥ

-0.24

çŁ¢

-0.24

<thead

-0.24

ç²ĴåŃĲ

-0.24

acre

-0.24

POSITIVE LOGITS

erus

0.28

éĺ²çĽĹ

0.27

BCM

0.26

ucz

0.26

akra

0.26

duk

0.26

è§

0.25

æĸ°æł¼å±Ģ

0.25

çīĪæĿĥå£°æĺİ

0.25

 DialogInterface

0.25

Activations Density 0.000%

No Known Activations

This feature has no known activations.