INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_27.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.27.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

 FITNESS

-0.27

)[-

-0.26

é¬»

-0.25

Leaks

-0.24

ardy

-0.24

åĽŀé¦ĸ

-0.24

rades

-0.23

ander

-0.23

 hier

-0.23

 fend

-0.23

POSITIVE LOGITS

ä¸įå¹³è¡¡

0.27

Ãªu

0.26

imuth

0.26

Ä±lÄ±yor

0.25

ucing

0.25

ibilidade

0.24

éĥ½åĸľæ¬¢

0.24

owane

0.24

Ä±nda

0.24

Ĥ¬

0.24

Activations Density 0.000%

No Known Activations

This feature has no known activations.