INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_32.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.32.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ä»ĸæĽ¾

-0.28

itud

-0.27

è°¯

-0.26

çĬį

-0.25

å¹¼ç¨ļ

-0.25

ardo

-0.25

æ¬ł

-0.24

è®¤çľŁåŃ¦ä¹ł

-0.24

cÃŃ

-0.23

è®¤çŁ¥

-0.23

POSITIVE LOGITS

you

0.31

 chlor

0.29

 selectable

0.28

 most

0.28

You

0.27

 filters

0.27

-you

0.27

 plast

0.27

 configurable

0.27

You

0.27

Activations Density 0.000%

No Known Activations

This feature has no known activations.