INDEX

Explanations

Size and deterioration

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

><

-0.25

 Dane

-0.25

èĨľ

-0.24

 glColor

-0.24

aments

-0.24

in

-0.24

imizer

-0.24

asty

-0.24

SG

-0.24

azon

-0.23

POSITIVE LOGITS

enga

0.29

ä¸Ģå¤©

0.28

ìĦ¸ìļĶ

0.28

åıĳå±ķæĸ¹åĲĳ

0.25

Consumer

0.24

ä½Ĩä»ĸä»¬

0.24

 telesc

0.24

ä¼Łå¤§å¤įåħ´

0.24

gradable

0.23

.getAs

0.23

Activations Density 0.002%

Size and deterioration

No Comments

No Known Activations