INDEX

Explanations

3

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

åĳ¨æľ«

-0.31

ä¸ĭåįĪ

-0.31

Saturday

-0.28

åĳ¨åħŃ

-0.28

antium

-0.28

åįĪåĲİ

-0.27

cases

-0.27

æĺŁæľŁ

-0.26

getOption

-0.26

 vegas

-0.26

POSITIVE LOGITS

 inverted

0.30

atta

0.25

IFF

0.24

//@

0.24

iff

0.24

ä¹Łåıªæľī

0.24

çº¯æ´ģ

0.24

del

0.24

 making

0.23

andin

0.23

Activations Density 0.013%

3

No Comments

No Known Activations