INDEX

Explanations

page numbers

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_25.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.25.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

hell

-0.30

hog

-0.27

alon

-0.26

çĽ¸å¯¹è¾ĥ

-0.25

riot

-0.25

 prof

-0.25

HELL

-0.25

ï¼ĮãĢĬ

-0.25

æµ©

-0.25

"profile

-0.24

POSITIVE LOGITS

éĢļ

0.27

ystems

0.25

points

0.24

ibly

0.24

çĤ¹

0.24

ìłĲ

0.24

çĮ´

0.24

ÃĮ

0.23

ä½¿

0.23

lay

0.23

Activations Density 0.899%

page numbers

No Comments

No Known Activations