INDEX

Explanations

Internet forum posts

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

çłľ

-0.33

æĤ¬æĮĤ

-0.29

 embarrass

-0.28

 quarter

-0.28

ç§°

-0.27

-quarter

-0.25

ç¨±

-0.25

missÃ£o

-0.25

å²ģæĹ¶

-0.24

letics

-0.24

POSITIVE LOGITS

 Animated

0.30

 Online

0.29

 Protected

0.28

 Attached

0.28

isoft

0.28

çļĦæĹ¶ä»£

0.28

å®Įåħ¨ä¸įåĲĮ

0.27

çĦī

0.26

 Terms

0.26

 Lost

0.26

Activations Density 0.006%

Internet forum posts

No Comments

No Known Activations