INDEX

Explanations

way

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_19.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.19.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

è¿Ļä»¶äºĭ

-0.24

ATEGY

-0.24

äºĭåħ³

-0.24

è¿Ļäºĭ

-0.24

 perk

-0.24

=cut

-0.24

è¿Ļæĺ¯æĪĳ

-0.24

è¿Ļä¸ªéĹ®é¢ĺ

-0.24

 Panic

-0.23

åľ¨ä¸ĢæĹģ

-0.23

POSITIVE LOGITS

-aff

0.28

èī¯

0.27

 guarantee

0.26

åı¶

0.25

bur

0.25

aceous

0.25

ä¿Ŀè¯ģ

0.24

Bur

0.23

çľģæķĻèĤ²

0.23

åĩĢ

0.23

Activations Density 0.175%

way

No Comments

No Known Activations