INDEX

Explanations

Sentence beginnings/ends and titles

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

æī¬

-0.29

uin

-0.26

buster

-0.26

 ends

-0.26

tek

-0.26

big

-0.25

yen

-0.25

èĩªçĶ±

-0.24

imir

-0.24

 concession

-0.24

POSITIVE LOGITS

åļı

0.27

çĽ¸åħ³ä¿¡æģ¯

0.27

çĽ¸åħ³åĨħå®¹

0.26

åĲĦè¡Į

0.26

åħĥå·¦åı³

0.26

pageTitle

0.25

ãģ®ãģĵãģ¨

0.24

 pageTitle

0.24

owe

0.24

 glands

0.24

Activations Density 0.000%

Sentence beginnings/ends and titles

No Comments

No Known Activations