INDEX

Explanations

into

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

rone

-0.30

 unfinished

-0.27

 specialised

-0.26

ÐµÑĢÑĮ

-0.26

inati

-0.25

/ph

-0.25

AppBundle

-0.24

enco

-0.23

partment

-0.23

kf

-0.23

POSITIVE LOGITS

è½©

0.29

te

0.28

arda

0.26

oku

0.25

peria

0.25

xies

0.25

ÐµÐ»Ð°

0.24

èģĶ

0.24

ep

0.23

ion

0.23

Activations Density 0.217%

into

No Comments

No Known Activations