INDEX

Explanations

grinding

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

utches

-0.31

otomy

-0.28

ä½ĵåĪ¶

-0.28

 assort

-0.27

ese

-0.27

utch

-0.26

emean

-0.26

-League

-0.25

Hut

-0.25

 constit

-0.25

POSITIVE LOGITS

æĲĵ

0.27

ç¡®åĪĩ

0.26

èĹī

0.25

od

0.25

 Lesb

0.25

 BaseController

0.25

eth

0.25

çľŁå®ŀ

0.24

_guid

0.24

ETH

0.24

Activations Density 0.022%

grinding

No Comments

No Known Activations