INDEX

Explanations

Yale

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

éĶµ

-0.27

 heads

-0.26

 lunch

-0.26

»¿

-0.26

åĹŁ

-0.25

URNS

-0.25

edis

-0.24

å¤´ä¸Ĭ

-0.24

likes

-0.24

 coincidence

-0.24

POSITIVE LOGITS

orate

0.36

ibernate

0.30

.dw

0.26

è´¯ç©¿

0.25

åħļåĴĮåĽ½å®¶

0.25

æ¹¾

0.25

è¿Ļå¼ł

0.25

ust

0.24

 settle

0.24

.toByteArray

0.24

Activations Density 0.005%

Yale

No Comments

No Known Activations