INDEX

Explanations

of

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.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

 patterns

-0.27

èĥ¼

-0.27

æĭħè´Ł

-0.26

 familiar

-0.25

 sÃ¡ng

-0.25

ä¸Ģå¦Ĥ

-0.25

åľ©

-0.24

ÙĬØŃ

-0.24

 saber

-0.23

?",

-0.23

POSITIVE LOGITS

ubber

0.27

uds

0.26

bpp

0.26

/pp

0.26

uids

0.25

InlineData

0.25

icked

0.24

 capped

0.24

OVE

0.24

å®Įç¾İçļĦ

0.24

Activations Density 0.002%

of

No Comments

No Known Activations