INDEX

Explanations

children

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_27.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.27.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ewhere

-0.30

ä»ĸå·²ç»ı

-0.29

bler

-0.29

åľĪ

-0.29

anda

-0.27

etta

-0.27

çĿĢçľ¼

-0.25

charged

-0.25

SEA

-0.25

anmar

-0.24

POSITIVE LOGITS

 learning

0.31

fox

0.31

 often

0.30

 learn

0.29

åŃ¦ä¹ł

0.28

DX

0.28

 ourselves

0.28

 always

0.27

xo

0.27

 especially

0.27

Activations Density 0.002%

children

No Comments

No Known Activations