INDEX

Explanations

zinc finger, fingers, dates

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_33.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.33.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 fingers

-0.36

 finger

-0.34

æĮĩ

-0.33

-f

-0.31

 toes

-0.30

 digit

-0.30

 fingerprint

-0.28

Comput

-0.27

èĤ¥

-0.27

DIG

-0.26

POSITIVE LOGITS

æ¸ħæ´ģ

0.29

åįģåŃĹ

0.28

Duo

0.27

éĢļè®¯åĳĺ

0.26

.clean

0.26

clean

0.26

 cleaner

0.25

anguage

0.25

å¹²åĩĢ

0.25

 clean

0.25

Activations Density 0.027%

zinc finger, fingers, dates

No Comments

No Known Activations