INDEX

Explanations

complex or problematic situations

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

Negative Logits

.Configure

-0.31

tur

-0.27

igure

-0.25

ifs

-0.24

atter

-0.24

subcategory

-0.24

æ·¡æ°´

-0.24

 entirety

-0.24

ATTER

-0.24

 advant

-0.24

POSITIVE LOGITS

/API

0.27

atoria

0.27

ãģĵãĤĵ

0.25

è°Ĳ

0.25

Sed

0.25

zb

0.25

è¿Ļä»¶äºĭ

0.25

è¿Ļäºĭ

0.24

iveness

0.24

 VOID

0.23

Activations Density 21.531%

complex or problematic situations

No Known Activations