INDEX

Explanations

years and dates

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

stood

-0.33

stin

-0.28

 Reich

-0.28

 delegated

-0.26

inant

-0.26

ister

-0.26

Umb

-0.26

ä¸»ä¹ī

-0.25

sme

-0.25

 connected

-0.25

POSITIVE LOGITS

åŃ£èĬĤ

0.28

è¿Ļæīįæĺ¯

0.26

eko

0.26

ç²¾

0.25

aines

0.25

ecs

0.24

.getInteger

0.24

çĻ¾åĪĨ

0.24

Â¦

0.24

pot

0.24

Activations Density 0.004%

years and dates

No Comments

No Known Activations