INDEX

Explanations

br

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

uart

-0.32

Communication

-0.27

 communication

-0.27

é¼¹

-0.25

urations

-0.25

communication

-0.25

 communicate

-0.25

communic

-0.25

aggi

-0.25

Pitch

-0.25

POSITIVE LOGITS

 Ernest

0.25

/static

0.25

Li

0.24

åıĤä¸İ

0.24

.gov

0.24

ERN

0.24

 References

0.23

è¡¾

0.23

//*[@

0.23

 Sands

0.23

Activations Density 0.004%

br

No Comments

No Known Activations