INDEX

Explanations

technical documents/web content

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_20.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.20.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

amation

-0.26

é¡¶

-0.26

finity

-0.26

çĬĬ

-0.26

Cup

-0.26

å½¢æĪĲçļĦ

-0.25

Enough

-0.25

 quoted

-0.24

 Enough

-0.24

å»º

-0.24

POSITIVE LOGITS

ril

0.27

æĬĢæľ¯äººåĳĺ

0.26

decorators

0.26

 supervisors

0.25

ÑĮÐµÐ²

0.24

 Navigate

0.24

åĲĦçº§

0.24

 avoids

0.24

aves

0.24

.Acc

0.24

Activations Density 14.472%

technical documents/web content

No Comments

No Known Activations