INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_30.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.30.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Gin

-0.28

posit

-0.26

è®£

-0.26

 Virt

-0.25

roma

-0.25

íĤ´

-0.25

 posi

-0.25

èµŀç¾İ

-0.25

 realtime

-0.25

äºĶæĺŁ

-0.24

POSITIVE LOGITS

ref

0.31

arov

0.30

urs

0.28

æľºåĻ¨

0.27

orth

0.26

ios

0.26

de

0.26

æļ®

0.25

 outs

0.25

 evening

0.25

Activations Density 0.890%

No Known Activations

This feature has no known activations.