INDEX

Explanations

Software files/versions

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_24.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.24.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

rese

-0.27

 begr

-0.26

rette

-0.26

GLOBALS

-0.26

Shr

-0.25

æĮ«

-0.25

getView

-0.24

hÃ¤

-0.24

æŀĭ

-0.24

enez

-0.24

POSITIVE LOGITS

erus

0.30

of

0.29

(s

0.26

iro

0.26

art

0.26

æİĢèµ·

0.25

 caught

0.25

or

0.24

 giveaway

0.23

in

0.23

Activations Density 0.537%

Software files/versions

No Comments

No Known Activations