INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_14.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.14.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

æ³¥

-0.27

ç§°

-0.27

ibe

-0.26

credits

-0.26

iative

-0.26

 extr

-0.25

æĥħæĦŁ

-0.25

aptive

-0.24

utm

-0.24

åħ¥åı£

-0.24

POSITIVE LOGITS

hop

0.26

åģĥ

0.24

æŃ¤ä¸¾

0.24

/frame

0.24

vens

0.24

è½Ń

0.24

Neg

0.23

_testing

0.23

lates

0.23

è½®æµģ

0.23

Activations Density 3.015%

No Known Activations

This feature has no known activations.