INDEX

Explanations

per

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_20.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.20.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

äº²

-0.30

anio

-0.28

è¦ģè¯´

-0.28

çĶ¨äºİ

-0.26

à´¦

-0.26

favor

-0.24

asco

-0.24

Pas

-0.24

 conv

-0.24

AAAAAAAA

-0.24

POSITIVE LOGITS

legate

0.27

 unleash

0.25

"--

0.24

å¥½åĲĹ

0.24

åºĹéĿ¢

0.24

INAL

0.23

 parten

0.23

”),

0.23

removeAttr

0.23

ngrx

0.23

Activations Density 0.623%

per

No Comments

No Known Activations