INDEX

Explanations

a

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.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

ç»ı

-0.29

åıĳ

-0.28

...

-0.27

...↵

-0.26

ÙĪØ©

-0.26

ÙĪØ§Øª

-0.25

ence

-0.25

 formulas

-0.25

 volte

-0.25

ory

-0.25

POSITIVE LOGITS

ustum

0.26

asper

0.26

edly

0.25

ForObject

0.25

edList

0.25

ä¸ªäº¤æĺĵ

0.25

 weddings

0.24

outil

0.24

SCALE

0.24

.ResponseWriter

0.24

Activations Density 0.013%

a

No Comments

No Known Activations