INDEX

Explanations

War

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

 Pearce

-0.29

ipse

-0.28

 Beds

-0.27

 Intl

-0.26

cef

-0.26

 Readonly

-0.24

ç¦³

-0.24

éĥ¨

-0.24

Pul

-0.24

 SAFE

-0.24

POSITIVE LOGITS

 opposing

0.34

Opp

0.30

 opposite

0.30

Opp

0.29

å¿«

0.27

otas

0.27

Ã¡k

0.26

å¿«éĢŁåıĳå±ķ

0.26

:view

0.26

æ³ģ

0.26

Activations Density 0.001%

War

No Comments

No Known Activations