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

äº²

-0.28

CollectionView

-0.26

ront

-0.26

cel

-0.25

çĦĺ

-0.24

èĩ§

-0.24

æ¯Ĥ

-0.24

è¿Ļä¸ªéĹ®é¢ĺ

-0.24

æ¶Ĥ

-0.24

éĺ´å½±

-0.24

POSITIVE LOGITS

ised

0.28

æĿĻ

0.27

.LA

0.25

 ordinary

0.25

aya

0.25

 Dickinson

0.25

æİĪè¯¾

0.25

 Ordinary

0.24

è°³

0.24

atted

0.24

Activations Density 0.007%

No Known Activations

This feature has no known activations.