INDEX

Explanations

Indonesia

np_max-act-logits · gemini-2.0-flash

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

nen

-0.34

åĲ¦

-0.33

mem

-0.33

mer

-0.32

mer

-0.29

meric

-0.28

Mer

-0.28

mem

-0.28

Mem

-0.26

ALAR

-0.26

POSITIVE LOGITS

ickle

0.28

èĹľ

0.26

ãĥ¼ãĤ¹

0.26

trÃ¤

0.26

çĤ¹å¤ļ

0.25

sob

0.25

.invokeLater

0.24

Ø§Ø¨Ø©

0.24

åİļåİļ

0.24

sov

0.24

Activations Density 0.004%

Indonesia

No Comments

No Known Activations