INDEX

Explanations

Quantities and limits

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_19.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.19.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

æĪĸå°Ĩ

-0.27

agna

-0.26

çİĭåŃĲ

-0.26

æĵįä½ľç³»ç»Ł

-0.26

è¯ģæĺİ

-0.25

è´¥

-0.25

croft

-0.24

 roleName

-0.24

è¿ĺæĺ¯å¾Ī

-0.24

éĻ£

-0.24

POSITIVE LOGITS

 central

0.26

 swing

0.26

ä¸Ńå¤®

0.25

_IL

0.25

 Central

0.25

åĵį

0.25

 trending

0.24

Where

0.24

èīĩ

0.24

ithe

0.23

Activations Density 0.098%

Quantities and limits

No Comments

No Known Activations