INDEX

Explanations

onic

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_20.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.20.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ableObject

-0.27

Lf

-0.26

ionate

-0.25

rade

-0.24

ecer

-0.24

xef

-0.24

.epsilon

-0.24

asca

-0.24

orget

-0.23

ritt

-0.23

POSITIVE LOGITS

jo

0.30

nas

0.29

ÅĤ

0.28

 Ð¿Ð¾Ð±

0.25

 mist

0.25

ule

0.25

loys

0.24

Anonymous

0.24

 anonymously

0.24

#End

0.24

Activations Density 24.640%

onic

No Comments

No Known Activations