INDEX

Explanations

Miscellaneous text

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

åĪĹ

-0.30

 presentation

-0.28

Pe

-0.27

 manifests

-0.27

 weren

-0.27

 manifest

-0.26

Presentation

-0.26

presentation

-0.26

VS

-0.25

 Bord

-0.25

POSITIVE LOGITS

(ext

0.29

çĶ³è¯ī

0.27

odate

0.25

 Ð·ÑĢÐµÐ½Ð¸Ñı

0.25

 Tháº£o

0.25

Ã¸d

0.25

belie

0.25

Ä±m

0.24

 ÑģÐ¾Ð³Ð»Ð°Ñģ

0.24

å«ģ

0.24

Activations Density 0.008%

Miscellaneous text

No Comments

No Known Activations