INDEX

Explanations

based

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

ahi

-0.28

-east

-0.27

 qualify

-0.25

mun

-0.24

 qualifies

-0.24

ä¸¤åĳ¨

-0.23

 furnish

-0.23

aries

-0.23

 pitching

-0.23

 occasionally

-0.22

POSITIVE LOGITS

 based

0.79

åŁºäºİ

0.73

based

0.66

 Based

0.63

Based

0.61

ä¾Ŀæį®

0.58

_based

0.54

ä¾Ŀæĵļ

0.52

æł¹æį®

0.49

ãģ«åŁºãģ¥

0.48

Activations Density 0.007%

based

No Comments

No Known Activations