INDEX

Explanations

light emission

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_31.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.31.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

flation

-0.30

 Fallon

-0.28

zers

-0.25

éĢĨè½¬

-0.25

[](

-0.24

 Instruments

-0.24

å±ķç¤º

-0.24

.ob

-0.24

blings

-0.24

 Show

-0.24

POSITIVE LOGITS

çĻ

0.38

åıĳåĩº

0.37

 emit

0.35

åıĳå°Ħ

0.35

 emits

0.35

emit

0.35

åıĳ

0.32

 åıĳ

0.31

çĻ¼

0.30

åıĳè¡Į

0.30

Activations Density 3.277%

light emission

No Comments

No Known Activations