INDEX

Explanations

solid

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

áºŃp

-0.28

 Ã¡mbito

-0.27

 yaygÄ±n

-0.25

["_

-0.25

åħ¶ä½Ļ

-0.25

similar

-0.24

æŃ£å¸¸

-0.23

ä¸ĬãģĮãĤĬ

-0.23

è¯Ń

-0.23

åŃĹä½ĵ

-0.23

POSITIVE LOGITS

ly

0.39

ity

0.36

izing

0.32

ization

0.32

ITY

0.29

ities

0.29

ized

0.29

mente

0.29

ising

0.28

aro

0.27

Activations Density 0.913%

solid

No Comments

No Known Activations