INDEX

Explanations

Code/technical text

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

 Bounty

-0.27

ursor

-0.27

å¦ĤæľŁ

-0.26

æŀ¶åŃĲ

-0.25

anela

-0.25

 createContext

-0.24

æķĪæŀľ

-0.24

æľ¬éĴ±

-0.24

 organisation

-0.23

 Venue

-0.23

POSITIVE LOGITS

lek

0.32

é©³

0.31

avers

0.28

 whims

0.28

 favor

0.27

tra

0.27

bach

0.26

awks

0.26

orde

0.26

rej

0.26

Activations Density 0.444%

Code/technical text

No Comments

No Known Activations