INDEX

Explanations

foreign languages and names

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

:block

-0.27

åģ»

-0.26

Cancelable

-0.26

èĤ½

-0.25

odable

-0.25

åı¤äºº

-0.25

åĮ»åŃ¦éĻ¢

-0.25

conference

-0.25

éĶ¦æłĩ

-0.24

={[

-0.24

POSITIVE LOGITS

onas

0.30

è²«

0.27

meer

0.27

Mae

0.26

illation

0.26

ilate

0.26

FI

0.26

æ³°

0.25

arth

0.24

fore

0.24

Activations Density 0.009%

foreign languages and names

No Comments

No Known Activations