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

Not in Any Lists

No Comments

Negative Logits

âĢ¢↵↵

-0.31

æĸ¹ãģ«

-0.28

ØªÙĩ

-0.26

 COPYRIGHT

-0.26

ä¸įè¯¥

-0.26

PAY

-0.26

apy

-0.25

éķĴ

-0.25

×ľ×ª

-0.25

ãĤĭãģ®ãģĮ

-0.25

POSITIVE LOGITS

éĢĴ

0.28

.Reverse

0.28

å¢ŀè¿Ľ

0.26

æ·±åº¦

0.25

èµĽ

0.25

 zipfile

0.25

 hybrid

0.24

æ·±å±Ĥæ¬¡

0.24

è¿ħ

0.24

.GetFiles

0.24

Activations Density 2.367%

No Known Activations

This feature has no known activations.