INDEX

Explanations

stop words

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

çı¥

-0.25

nothrow

-0.25

åĴĮçĿ¦

-0.24

Vij

-0.24

uchen

-0.24

Vit

-0.24

)="

-0.24

fel

-0.24

åĩº

-0.23

redient

-0.23

POSITIVE LOGITS

illis

0.27

keepers

0.26

ycles

0.26

 replacement

0.26

Zip

0.25

hid

0.25

hab

0.25

arts

0.24

Zip

0.24

.Management

0.24

Activations Density 0.010%

stop words

No Comments

No Known Activations