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

çľģæķĻèĤ²

-0.36

repos

-0.28

å¾Ģå¾Ģæĺ¯

-0.27

aro

-0.27

 Tune

-0.26

 tune

-0.26

.setAuto

-0.26

arding

-0.25

éĺ¼

-0.24

WithMany

-0.24

POSITIVE LOGITS

éļĲå½¢

0.27

è¿ĩ

0.25

ableView

0.24

 Cler

0.24

à¹Ģà¸Ńà¸ĩ

0.24

æ§Ľ

0.23

 filled

0.23

 Haley

0.23

å½ĵå¹´

0.23

bles

0.23

Activations Density 0.002%

No Known Activations

This feature has no known activations.