INDEX

Explanations

name and filename

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_25.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.25.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

olest

-0.27

éĵİ

-0.25

Accessory

-0.24

.SelectedIndex

-0.24

indy

-0.24

ÐķÐĿ

-0.24

ivre

-0.24

))?

-0.23

NavController

-0.23

inery

-0.23

POSITIVE LOGITS

åĲįç§°

0.81

 name

0.77

åĲįåŃĹ

0.69

çļĦåĲįåŃĹ

0.66

 Name

0.63

 filename

0.63

name

0.60

 title

0.60

å§ĵåĲį

0.59

_name

0.56

Activations Density 0.978%

name and filename

No Comments

No Known Activations