INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

ç¬¬ä¸ĢèĬĤ

-0.28

 Irvine

-0.27

ivities

-0.25

/MIT

-0.25

plot

-0.25

resultCode

-0.24

ç¥¨

-0.24

_workers

-0.24

ToSelector

-0.23

lush

-0.23

POSITIVE LOGITS

Me

0.29

.Me

0.27

Me

0.26

æ³®

0.25

$ret

0.25

(dr

0.24

åħħæ»¡

0.24

ä¸Ńä¿Ħ

0.24

å°Ĭæķ¬

0.24

me

0.23

Activations Density 0.001%

No Known Activations

This feature has no known activations.