INDEX

Explanations

have

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

miss

-0.27

åĿļ

-0.25

(('

-0.25

'('

-0.25

SDL

-0.24

ä½¿äºº

-0.24

.='

-0.23

EC

-0.23

åĤ»

-0.23

.ali

-0.23

POSITIVE LOGITS

Ļ¨

0.28

å®¶éĹ¨åı£

0.28

oader

0.28

ossip

0.27

horse

0.27

Ã¶m

0.26

éĩįä¸Ń

0.26

Ð³ÐµÑĢ

0.26

ibus

0.25

 tutoring

0.25

Activations Density 0.006%

have

No Comments

No Known Activations