INDEX

Explanations

neutral

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

æīĵèµ¢

-0.28

reb

-0.27

batim

-0.26

/en

-0.24

-switch

-0.24

_EN

-0.24

.ObjectModel

-0.24

ìŀ¥ìĿĦ

-0.24

 ÄĳÃ¡nh

-0.24

enate

-0.23

POSITIVE LOGITS

SELF

0.29

 SELF

0.27

Ã¼ss

0.26

ople

0.26

.Handler

0.26

Fuse

0.25

_attach

0.25

èµĺ

0.25

oins

0.24

(compact

0.24

Activations Density 0.088%

neutral

No Comments

No Known Activations