INDEX

Explanations

but

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

æŃ£éĿ¢

-0.28

 tentative

-0.28

 tá»ķ

-0.26

å¤ªå¹³

-0.26

çľ¼çļ®

-0.25

(QtCore

-0.25

_fact

-0.25

åİŁåĪĽ

-0.24

æĸ¯åŁº

-0.24

æĮĩæľĽ

-0.23

POSITIVE LOGITS

','-

0.28

acht

0.28

ihad

0.26

==-

0.26

 semantics

0.25

eway

0.24

args

0.24

 rendition

0.24

Ã¡st

0.24

/as

0.23

Activations Density 0.036%

but

No Comments

No Known Activations