INDEX

Explanations

of

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.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

æķŀå¼Ģ

-0.28

ç¦ıå¾·

-0.27

 orderId

-0.27

æ´½

-0.27

åħ¬å¹³

-0.26

_advance

-0.26

matches

-0.25

MATCH

-0.25

 bees

-0.25

lot

-0.24

POSITIVE LOGITS

Ã¶h

0.29

ning

0.26

 ;č↵č↵

0.25

æ·±åĬłå·¥

0.24

Old

0.24

è¾ĵ

0.24

çĩĥ

0.24

ìŀī

0.24

ç»İ

0.24

_present

0.24

Activations Density 0.036%

of

No Comments

No Known Activations