INDEX

Explanations

court cases

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.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

/if

-0.25

ãĤĤãģ®

-0.23

ajar

-0.23

à¸´à¸ĩ

-0.23

ORIZ

-0.22

OrFail

-0.22

 localize

-0.22

-good

-0.22

nip

-0.22

itta

-0.21

POSITIVE LOGITS

åİ»äºĨ

0.27

åıĺå½¢

0.24

 Herz

0.23

ederation

0.23

->[

0.23

ÐµÐ»Ð¸

0.23

dere

0.22

PLEX

0.22

atures

0.22

å²ģ

0.22

Activations Density 0.250%

court cases

No Comments

No Known Activations