INDEX

Explanations

vote

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

ibern

-0.27

chers

-0.26

 nors

-0.25

utory

-0.24

 Getty

-0.24

.port

-0.24

åħ³åģľ

-0.24

Tyr

-0.24

enment

-0.24

_Port

-0.23

POSITIVE LOGITS

eso

0.27

tap

0.26

æ¹ĸåĮº

0.25

èķ»

0.25

venient

0.25

INCT

0.25

createForm

0.25

tap

0.24

 CActive

0.24

SED

0.24

Activations Density 0.047%

vote

No Comments

No Known Activations