INDEX

Explanations

of

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 search

-0.27

uite

-0.25

éĬ®

-0.25

è¿ĶåĽŀæĲľçĭĲ

-0.25

Bro

-0.25

 shields

-0.25

æ½ľ

-0.24

çŃĸ

-0.24

 Mixed

-0.24

 mixed

-0.24

POSITIVE LOGITS

æŃ¤é¡¹

0.28

æľ¬æĽ¸

0.28

æŃ¤æĸĩ

0.28

groupName

0.27

 plais

0.27

seat

0.27

ieux

0.25

éĹ´éļĻ

0.25

ivet

0.24

ä¸Ĭåİ»

0.24

Activations Density 0.128%

of

No Comments

No Known Activations