INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_19.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.19.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ungan

-0.28

æĽ°

-0.26

otics

-0.25

å¸¦èµ°

-0.25

owitz

-0.25

ederation

-0.25

çŃĶåºĶ

-0.25

zoek

-0.24

åľ¨ä¸Ģ

-0.24

 crusher

-0.24

POSITIVE LOGITS

SCO

0.28

çĶ¨æĪ·

0.26

ļĮ

0.26

é£Ļ

0.25

.getInteger

0.25

uhan

0.25

è¾¹

0.24

æĹ¢æľī

0.23

 Dialog

0.23

dialog

0.23

Activations Density 0.010%

No Known Activations

This feature has no known activations.