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

åĪĩæį¢

-0.25

æķ¦

-0.25

éĺ¶æ®µ

-0.24

 handleMessage

-0.24

sville

-0.23

åĪĨæł¡

-0.23

getError

-0.23

oise

-0.23

hed

-0.23

uggy

-0.23

POSITIVE LOGITS

çļĦä¾ĭåŃĲ

0.34

kes

0.29

ä¾ĭåŃĲ

0.27

anos

0.27

atorium

0.27

æ·Ģ

0.26

idos

0.25

ì¹Ń

0.25

çī¹æĿĥ

0.25

ä½¿

0.25

Activations Density 0.089%

No Known Activations

This feature has no known activations.