INDEX

Explanations

in

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

ä¹ĭä¹¡

-0.28

Disconnect

-0.27

èĲ¤

-0.27

ncy

-0.26

Ã¼m

-0.25

 punct

-0.25

_CONFIGURATION

-0.24

Ã¼s

-0.24

_href

-0.24

 probable

-0.24

POSITIVE LOGITS

icast

0.26

ATS

0.24

ATS

0.24

adera

0.24

blade

0.24

_UNUSED

0.24

<?>>

0.24

(er

0.23

villa

0.23

ene

0.23

Activations Density 0.001%

in

No Comments

No Known Activations