INDEX

Explanations

Code, technical text

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

çĤŃ

-0.31

inea

-0.31

%)↵↵

-0.28

çĻ¾å®¶

-0.27

ÃŃstica

-0.26

“↵↵

-0.26

-chan

-0.25

éĢģ

-0.25

 )}↵↵

-0.25

	define

-0.24

POSITIVE LOGITS

 Manufact

0.28

ARAM

0.25

lid

0.25

something

0.25

lash

0.25

 fmap

0.24

æĥ³äºĨ

0.24

inn

0.24

 pract

0.24

 Educ

0.23

Activations Density 0.006%

Code, technical text

No Comments

No Known Activations