INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.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¸įåĸľæ¬¢

-0.25

 Breath

-0.25

_RET

-0.24

åĪĨæŀĲ

-0.24

åĢĴ

-0.24

éĤ£ä½į

-0.24

Tot

-0.23

pac

-0.23

rep

-0.23

åı£ç¢ĳ

-0.23

POSITIVE LOGITS

iting

0.28

IpAddress

0.28

à¦ĵ

0.28

NodeType

0.27

æ¹ĥ

0.26

ahun

0.25

 khÃ³a

0.25

uable

0.25

eway

0.24

åºĲ

0.24

Activations Density 0.002%

No Known Activations

This feature has no known activations.