INDEX

Explanations

the

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

dw

-0.28

dess

-0.26

orting

-0.25

éĢıè§Ĩ

-0.25

 ideally

-0.25

åĪ°

-0.25

æİĴæ¯Ĵ

-0.25

Bri

-0.24

ä¼¼çļĦ

-0.24

POSITIVE LOGITS

Wild

0.32

oplast

0.28

ulia

0.28

 Wild

0.26

.unpack

0.26

 wild

0.26

ured

0.25

hon

0.24

Orn

0.24

imid

0.24

Activations Density 0.087%

the

No Comments

No Known Activations