INDEX

Explanations

aling

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

nia

-0.33

iaz

-0.31

ICE

-0.30

IPH

-0.29

TURN

-0.28

 TURN

-0.27

ias

-0.27

ACES

-0.26

ice

-0.25

èĹ©

-0.25

POSITIVE LOGITS

 matÃ©

0.28

 burial

0.27

åĩºãģĹ

0.26

 uploading

0.26

 uploads

0.26

æĿ¾

0.25

isle

0.25

è¿ĩ

0.25

 heavens

0.25

ymax

0.24

Activations Density 0.013%

aling

No Comments

No Known Activations