INDEX

Explanations

iv

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

é¢ľèī²

-0.32

çļĦé¢ľèī²

-0.31

è§Ħ

-0.29

ä¸ĢåĪĩ

-0.28

äººçĶŁ

-0.28

ursor

-0.27

æ¨£

-0.27

 color

-0.26

æ¨¡æł·

-0.26

éĹ´

-0.25

POSITIVE LOGITS

hood

0.27

 Standing

0.27

ä¸Ģä¸ĸ

0.26

 hood

0.26

%%%%

0.26

çĹ«

0.26

è¿Ļæł·åģļ

0.25

nown

0.25

çŀİ

0.24

alytics

0.24

Activations Density 0.059%

iv

No Comments

No Known Activations