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

Not in Any Lists

No Comments

Negative Logits

åħħ

-0.29

obox

-0.26

éĢļçķħ

-0.26

æĹłå£°

-0.25

æľ¬

-0.25

éĿĴ

-0.25

 automatic

-0.24

é«ĺçº§

-0.24

æıĲåıĬ

-0.23

reading

-0.23

POSITIVE LOGITS

soon

0.31

adem

0.30

.isArray

0.28

):-

0.28

ailable

0.27

alley

0.27

agal

0.25

aes

0.25

aad

0.25

éĶĢåĶ®æĶ¶åħ¥

0.24

Activations Density 0.002%

No Known Activations

This feature has no known activations.