INDEX

Explanations

Numbers and symbols

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

st

-0.28

å®ļåĲĳ

-0.27

Counts

-0.26

è®©åŃ©åŃĲ

-0.26

ottle

-0.26

iona

-0.24

æĳ©

-0.24

äº¿åĲ¨

-0.24

tym

-0.24

ormsg

-0.24

POSITIVE LOGITS

tright

0.27

/MPL

0.26

publication

0.26

 visuals

0.25

 literature

0.25

lds

0.24

ä¸¤å²¸

0.24

ServletResponse

0.24

imated

0.23

 opposite

0.23

Activations Density 0.011%

Numbers and symbols

No Comments

No Known Activations