INDEX

Explanations

Congress

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

å¹´åĨħ

-0.27

 york

-0.26

erra

-0.26

çļĦäºĭæĥħ

-0.25

åĸľæĤ¦

-0.25

 punched

-0.25

å²©

-0.24

mgr

-0.24

 Yorkers

-0.24

 Roch

-0.23

POSITIVE LOGITS

KEN

0.30

GIN

0.26

æĶ¾å¿ĥ

0.26

ä»ĸä»¬æĺ¯

0.25

æķ´ä¸ª

0.25

åĿĩåĮĢ

0.25

KT

0.24

åħ¨èº«

0.24

è¿ĩæķı

0.24

ä¸ļä½Ļ

0.24

Activations Density 0.040%

Congress

No Comments

No Known Activations