INDEX

Explanations

names starting with Gust

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_32.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.32.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

mun

-0.28

inet

-0.28

ä¿®

-0.26

 cast

-0.26

 rate

-0.25

lÄ±ÄŁÄ±n

-0.25

mer

-0.25

Dec

-0.25

CP

-0.25

casts

-0.25

POSITIVE LOGITS

 Valk

0.32

æŀī

0.29

Luck

0.27

çĨ¨

0.26

OTH

0.25

 halk

0.25

ç»ıçºª

0.25

Ľå»º

0.25

amas

0.24

ä¸ĢåĽ¢

0.24

Activations Density 0.002%

names starting with Gust

No Comments

No Known Activations