INDEX

Explanations

of

np_max-act · gemini-2.0-flash

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-vis

-0.27

ç§Ģ

-0.25

British

-0.24

oppel

-0.24

Nov

-0.23

 redo

-0.23

.$.

-0.23

çĸıå¯¼

-0.23

NO

-0.23

 mixture

-0.23

POSITIVE LOGITS

imers

0.32

ypi

0.29

ormap

0.28

çķı

0.28

å¾Ĺå¤©

0.27

niest

0.26

 polish

0.25

mpl

0.25

ÑĦÐµÑĢ

0.24

present

0.24

Activations Density 0.333%

of

No Comments

No Known Activations