INDEX

Explanations

and

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

	inline

-0.29

é¥¶

-0.27

trÃ©

-0.26

mans

-0.24

çĸĹæ³ķ

-0.24

strar

-0.24

åĿĢ

-0.23

 minden

-0.23

çłģ

-0.23

èĭ¦èĭ¦

-0.23

POSITIVE LOGITS

 pole

0.28

angent

0.27

 separat

0.26

ONGL

0.26

ei

0.25

yun

0.25

ong

0.25

 island

0.25

 pivot

0.24

SVC

0.24

Activations Density 0.128%

and

No Comments

No Known Activations