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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ä¾Ŀæ³ķè¿½ç©¶

-0.28

glas

-0.28

 partially

-0.26

è¹Ħ

-0.26

è¶Ĭ

-0.26

tas

-0.25

 preferred

-0.25

Ð¶Ñĥ

-0.25

icity

-0.25

ä¸Ģä¸ªéĹ®é¢ĺ

-0.25

POSITIVE LOGITS

 ceil

0.26

-priced

0.25

 reports

0.25

 AppModule

0.24

è¿ĩåİ»

0.24

æīĵåį°

0.24

 priced

0.24

olec

0.23

/animations

0.23

MU

0.23

Activations Density 0.003%

No Known Activations

This feature has no known activations.