INDEX

Explanations

moisture

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

Getty

-0.25

arshal

-0.24

åļİ

-0.24

 Getty

-0.23

 mobility

-0.23

pot

-0.23

æĻĵ

-0.23

 coming

-0.23

psz

-0.23

å®īæĬļ

-0.23

POSITIVE LOGITS

emen

0.28

ificate

0.28

emon

0.28

itre

0.27

ements

0.26

rent

0.25

ë¦¿

0.25

alez

0.25

ship

0.24

FUL

0.24

Activations Density 0.821%

moisture

No Comments

No Known Activations