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

 Frid

-0.29

è§Ĩ

-0.26

çľĭäºĨä¸Ģçľ¼

-0.26

è¦ģçľĭ

-0.26

åĬ²

-0.26

 Constraints

-0.24

 constr

-0.24

 Transcript

-0.24

åĭģ

-0.24

=@"

-0.24

POSITIVE LOGITS

.sourceforge

0.27

è¶¸

0.26

rror

0.26

ãģĹãģ¦ãģĬãģı

0.26

æ±ĩ

0.26

-pagination

0.25

 intel

0.24

-rounded

0.24

lan

0.24

Meanwhile

0.24

Activations Density 0.002%

No Known Activations

This feature has no known activations.