INDEX

Explanations

letter v

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_32.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.32.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

æĸĳ

-0.28

CLUD

-0.28

ella

-0.27

æ¶Ī

-0.27

TURE

-0.26

uki

-0.26

 banda

-0.26

æ³¨æĺİæĿ¥æºĲ

-0.25

Dip

-0.25

dip

-0.25

POSITIVE LOGITS

èĭ±çī¹

0.28

/Library

0.28

 Minute

0.26

 minute

0.25

AGMA

0.25

ä¸Ģè§Ĵ

0.25

XmlNode

0.25

 given

0.24

ocrin

0.24

vÃ©

0.23

Activations Density 0.002%

letter v

No Comments

No Known Activations