INDEX

Explanations

but

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

æ¤½

-0.29

avis

-0.27

íģ°

-0.25

ä¸įåĩº

-0.25

å®īä¸ľ

-0.25

 instruments

-0.24

ä½Ĩæĺ¯å¯¹äºİ

-0.24

strument

-0.24

rote

-0.24

ikk

-0.24

POSITIVE LOGITS

 also

0.60

 anche

0.45

ä¹Łè¦ģ

0.45

 tambiÃ©n

0.44

also

0.44

 even

0.43

 ALSO

0.42

 auch

0.42

 tambÃ©m

0.41

ä¹Ł

0.41

Activations Density 0.015%

but

No Comments

No Known Activations