INDEX

Explanations

scientific papers

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

yme

-0.28

ä¸įçĦ¶

-0.27

è®¾è®¡æĸ¹æ¡Ī

-0.26

 OTHERWISE

-0.26

è¿Ļä¸ªåľ°æĸ¹

-0.25

ãģĭãģªãģĦ

-0.25

ãģ¤ãģı

-0.25

 medicines

-0.25

_METADATA

-0.25

Pro

-0.24

POSITIVE LOGITS

.setAuto

0.28

wrap

0.25

 surround

0.25

 backing

0.24

AJOR

0.24

jel

0.24

ÂŃtion

0.24

qual

0.24

 factorial

0.24

 isNaN

0.23

Activations Density 0.041%

scientific papers

No Comments

No Known Activations