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

åŃ¸éĻ¢

-0.31

 Rough

-0.27

Amb

-0.27

atel

-0.27

æĥļ

-0.26

è§ĤæľĽ

-0.26

Amb

-0.25

Anyway

-0.25

ä¸İåĲ¦

-0.24

cname

-0.24

POSITIVE LOGITS

åĬłæ·±

0.27

å¼¹

0.26

ji

0.26

Nano

0.26

lico

0.26

imm

0.25

agnar

0.25

 nano

0.24

inar

0.24

jections

0.24

Activations Density 0.040%

No Known Activations

This feature has no known activations.