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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ä¸įå¤§

-0.28

çĶŁèĤ²

-0.26

åĲĮä¸ļ

-0.25

Nom

-0.25

ç¢İ

-0.25

åĲĵ

-0.24

 consequence

-0.24

é«ĺå±Ĥæ¬¡

-0.23

FFF

-0.23

çħ®

-0.23

POSITIVE LOGITS

voke

0.29

åı

0.29

oplay

0.27

åĨħå¤ĸ

0.26

 communicator

0.25

çŃ¾åŃĹ

0.25

|.

0.25

entina

0.24

ationToken

0.24

CADE

0.24

Activations Density 0.060%

of

No Comments

No Known Activations