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

orton

-0.28

æ¶ķ

-0.27

åĩĨ

-0.26

Pres

-0.26

es

-0.26

å¤ĩ

-0.26

çī©è´¨

-0.26

éĢļ

-0.25

or

-0.25

å¢Ł

-0.25

POSITIVE LOGITS

è¿Ļä¸ĢåĪĩ

0.28

erox

0.27

 bookmarks

0.26

azine

0.25

NSK

0.25

 testimon

0.24

 anecd

0.24

hsv

0.24

cedures

0.24

 ×¤×ª

0.24

Activations Density 0.799%

No Known Activations

This feature has no known activations.