INDEX

Explanations

email addresses, 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

 promot

-0.30

DatePicker

-0.27

æĭ¦æĪª

-0.27

ä¸Ģæł·çļĦ

-0.27

 darkest

-0.26

rai

-0.25

 evid

-0.24

å¤´

-0.24

æŀĦçŃĳ

-0.24

 manoe

-0.24

POSITIVE LOGITS

_supply

0.26

BILL

0.25

stown

0.25

å®¹

0.25

stab

0.25

IVEN

0.24

_IMPORTED

0.24

ìķĪ

0.24

Ã´i

0.24

 supply

0.24

Activations Density 0.058%

email addresses, code

No Comments

No Known Activations