INDEX

Explanations

about on

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

åĤ»

-0.32

attachments

-0.27

 Examiner

-0.26

antha

-0.25

åĢı

-0.25

cyc

-0.25

_cmos

-0.25

 '-')

-0.24

 automÃ¡t

-0.24

%@

-0.24

POSITIVE LOGITS

desc

0.28

è´

0.27

Desc

0.27

èĨº

0.27

AY

0.27

éĹ®ä»ĸ

0.26

ç»ĻåĬĽ

0.26

Did

0.26

 Desc

0.25

èĦ

0.25

Activations Density 0.003%

about on

No Comments

No Known Activations