INDEX

Explanations

Abbreviations

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

ç½®æį¢

-0.31

imi

-0.28

viewport

-0.27

ensi

-0.26

å¯Ħ

-0.26

pl

-0.26

ãĥĵãĤ¸

-0.25

çĶ¸

-0.25

isten

-0.24

gon

-0.24

POSITIVE LOGITS

.echo

0.29

 Echo

0.29

éĶĿ

0.29

æĦıæĥ³ä¸įåĪ°

0.27

_echo

0.26

æĦıå¤ĸ

0.26

 echoes

0.25

leine

0.25

Backing

0.24

æķ£æŃ¥

0.24

Activations Density 0.381%

Abbreviations

No Comments

No Known Activations