INDEX

Explanations

parties

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_0.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.0.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Rid

-0.28

 tighter

-0.27

_lift

-0.26

æĮĤåı·

-0.26

éľ²åĩº

-0.26

egot

-0.26

 pars

-0.26

æİ§

-0.25

anine

-0.24

ĭè¯ķ

-0.24

POSITIVE LOGITS

å·¥ä½ľæĬ¥åĳĬ

0.28

 Staples

0.27

’s

0.27

ware

0.25

ian

0.25

åĲĦé¡¹å·¥ä½ľ

0.25

åĬŀäºĭ

0.24

<_

0.24

rou

0.24

inf

0.23

Activations Density 3.571%

parties

No Comments

No Known Activations