INDEX

Explanations

barriers

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

kwargs

-0.26

remium

-0.26

å²Ĺ

-0.25

çī¹ä»·

-0.25

å´

-0.24

 screened

-0.24

 kostenlos

-0.23

 cheek

-0.23

ocus

-0.23

inox

-0.23

POSITIVE LOGITS

åĬ©

0.28

unos

0.27

Ĩµ

0.27

dings

0.26

rides

0.25

åıĹå®³

0.25

è¡·

0.25

æŁł

0.25

 addAction

0.25

izens

0.25

Activations Density 0.047%

barriers

No Comments

No Known Activations