INDEX

Explanations

code/technical documentation

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_19.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.19.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

eus

-0.26

 LETTER

-0.25

å¿ħè¦ģãģĮãģĤãĤĬãģ¾ãģĻ

-0.25

OfFile

-0.24

 Sofa

-0.24

nown

-0.23

vang

-0.23

á»Ļi

-0.23

èĢĮéĿŀ

-0.23

åĲķå¸ĥ

-0.23

POSITIVE LOGITS

çĽ¸åĲĮ

0.40

 equival

0.36

 equivalent

0.36

çĽ¸åĲĮçļĦ

0.35

 same

0.35

 similar

0.34

Same

0.34

åĲĮæł·çļĦ

0.33

 essentially

0.33

çĽ¸ä¼¼

0.32

Activations Density 0.019%

code/technical documentation

No Comments

No Known Activations