INDEX

Explanations

returning or leaving

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

vement

-0.28

ìĤ¬íķŃ

-0.27

åĭŀ

-0.26

?action

-0.25

 WÃ¤h

-0.24

.singleton

-0.24

.GetValue

-0.24

 segreg

-0.23

 miesz

-0.23

áºµ

-0.23

POSITIVE LOGITS

baum

0.27

-indent

0.26

urray

0.26

æµģæ°´

0.25

æĪĳå¾Ī

0.25

isable

0.25

Minute

0.25

 Minute

0.24

ocado

0.24

 Lucky

0.23

Activations Density 0.026%

returning or leaving

No Comments

No Known Activations