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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 competitive

-0.31

endent

-0.26

 mere

-0.26

ç«ŀ

-0.26

.loop

-0.26

 Competitive

-0.25

 Ð½Ð°Ð»Ð¸ÑĩÐ¸Ðµ

-0.25

 recycle

-0.24

 disruptive

-0.24

 throat

-0.23

POSITIVE LOGITS

fm

0.30

æ¯Ķçİĩ

0.28

é£¨

0.27

_bm

0.26

åĬŁè¯¾

0.26

inalg

0.26

ÇĲ

0.25

åĿĬ

0.24

æĪ·

0.24

ç¢°

0.24

Activations Density 0.001%

of

No Comments

No Known Activations