INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_20.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.20.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

_EC

-0.31

EC

-0.27

Ke

-0.26

dg

-0.25

Ke

-0.25

é¡Ĩ

-0.25

(EC

-0.25

 participant

-0.24

beck

-0.24

esture

-0.24

POSITIVE LOGITS

/original

0.27

å£°

0.27

è·¯åı£

0.26

ToJson

0.25

.Broadcast

0.25

æµģ

0.24

è¿Ķ

0.24

çİ°å®ŀçĶŁæ´»

0.24

å¤ĸ

0.24

::$

0.24

Activations Density 76.173%

No Known Activations

This feature has no known activations.