INDEX

Explanations

and/or commas

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

çĺ¢

-0.28

awy

-0.27

ä¼¤

-0.26

ìĩĦ

-0.26

 uyar

-0.25

åĦĨ

-0.24

Todo

-0.24

okit

-0.24

fx

-0.24

VEL

-0.24

POSITIVE LOGITS

å¿ĥå¤´

0.31

Extern

0.28

olut

0.28

 extern

0.27

	extern

0.26

eti

0.25

 licensors

0.25

.Factory

0.25

illin

0.25

alborg

0.25

Activations Density 0.102%

and/or commas

No Comments

No Known Activations