INDEX

Explanations

computer networking

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

emas

-0.30

 yourselves

-0.27

lesc

-0.26

æĵįçºµ

-0.26

 Probe

-0.26

Era

-0.25

Ã©ra

-0.25

tones

-0.25

 Contr

-0.25

 Techn

-0.25

POSITIVE LOGITS

ÑģÑĭÐ»

0.28

åĩºåĩ»

0.27

rijk

0.26

åĨ³

0.25

æĻķ

0.25

fan

0.24

Ø§Ø·

0.24

 liá»ģn

0.24

fan

0.23

 personne

0.23

Activations Density 0.020%

computer networking

No Comments

No Known Activations