INDEX

Explanations

al

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

atories

-0.30

ç«Ļç«ĭ

-0.30

æ´¥

-0.27

aN

-0.27

ç§įç±»

-0.26

-budget

-0.25

 busiest

-0.25

ä¸İåĲ¦

-0.25

osti

-0.25

 treadmill

-0.25

POSITIVE LOGITS

Lower

0.27

è¿ĺæĺ¯ä¼ļ

0.26

 cabo

0.26

æīĵçĲĥ

0.26

gba

0.26

é¹ħ

0.25

éĩįåĽŀ

0.24

é¬Ł

0.24

SearchParams

0.24

gm

0.24

Activations Density 0.069%

al

No Comments

No Known Activations