INDEX

Explanations

Code and licensing

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_27.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.27.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

 nutrition

-0.31

nut

-0.30

 hung

-0.29

èĲ¥åħ»

-0.28

nut

-0.26

æİĽ

-0.26

illo

-0.26

fÃ¼

-0.26

nu

-0.25

åŃĺ

-0.25

POSITIVE LOGITS

.tf

0.27

ransition

0.27

æ¸ħæĻ¨

0.26

SYM

0.26

æľĢåĲİä¸Ģä¸ª

0.26

å½Ĵå±ŀ

0.25

LastError

0.25

laÅŁ

0.25

å¡ĳ

0.24

WebpackPlugin

0.24

Activations Density 0.005%

Code and licensing

No Comments

No Known Activations