INDEX

Explanations

ust

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

çħ§

-0.28

aland

-0.26

ICH

-0.25

Slash

-0.25

 nostr

-0.25

SSI

-0.25

Prince

-0.24

",(

-0.24

/hash

-0.24

 twins

-0.23

POSITIVE LOGITS

 mÃ¹

0.27

è¯»èĢħ

0.25

umped

0.25

 orthogonal

0.24

 systems

0.24

DataContract

0.24

èī¯å¥½

0.24

ideos

0.24

formedURLException

0.24

èªŃ

0.24

Activations Density 0.033%

ust

No Comments

No Known Activations