INDEX

Explanations

Programming code

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

åħĪå¯¼

-0.28

REDIT

-0.28

RAINT

-0.28

redit

-0.27

åĻ¨

-0.27

arium

-0.26

UrlParser

-0.25

Ent

-0.25

IMER

-0.24

Ent

-0.24

POSITIVE LOGITS

 sense

0.27

 ÑģÐ»ÑĥÑĩÐ°

0.27

spread

0.27

lda

0.27

ublic

0.24

å¸Ĥåİ¿

0.24

 scaff

0.24

 Rolls

0.24

çģ«çĪĨ

0.24

asted

0.23

Activations Density 0.026%

Programming code

No Comments

No Known Activations