INDEX

Explanations

Sus

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

iros

-0.28

idal

-0.28

syn

-0.26

ARA

-0.26

 giÃ³

-0.25

RIX

-0.25

bsp

-0.25

SY

-0.24

iges

-0.24

quan

-0.24

POSITIVE LOGITS

_attrib

0.31

ipel

0.27

elier

0.26

itive

0.25

æ²īæµ¸

0.25

propri

0.24

cribed

0.24

ured

0.24

åĳĪçİ°

0.24

ientes

0.23

Activations Density 0.037%

Sus

No Comments

No Known Activations