INDEX

Explanations

location/placement or general information

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

 across

-0.31

AJ

-0.29

 Across

-0.28

åĲĦåĽ½

-0.27

Fut

-0.27

ä¸ĸçķĮåĲĦåĽ½

-0.26

åĲĦçľģ

-0.26

åĲĦåİ¿

-0.26

,O

-0.26

Aj

-0.25

POSITIVE LOGITS

è½»è½»

0.28

å¨ī

0.27

.pkg

0.25

Embedded

0.25

STEM

0.24

less

0.24

ç²½

0.24

ãĥªãĤ¹ãĥĪ

0.24

à¸Ħà¸¡

0.24

eren

0.24

Activations Density 0.098%

location/placement or general information

No Comments

No Known Activations