INDEX

Explanations

Military/Warfare contexts

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ä¸¤å®¶

-0.28

imonial

-0.27

æī£

-0.26

IPH

-0.25

å°Ħæīĭ

-0.25

ä¸įåģļ

-0.25

urar

-0.24

åıĮè¾¹

-0.24

 unlink

-0.24

 removeAll

-0.23

POSITIVE LOGITS

umi

0.30

.promise

0.28

 scri

0.28

olia

0.28

ç»ĵçŁ³

0.27

 slate

0.25

æłĩ

0.25

á»ĵn

0.25

 expectedResult

0.24

AGIC

0.24

Activations Density 0.000%

Military/Warfare contexts

No Comments

No Known Activations