INDEX

Explanations

ala

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

Negative Logits

aff

-0.34

 affinity

-0.31

aff

-0.30

IJ

-0.30

Aff

-0.28

æĹĭ

-0.26

immer

-0.25

autop

-0.25

éĹ²

-0.25

IOD

-0.24

POSITIVE LOGITS

Ang

0.29

omatic

0.28

è¡¡

0.27

åħ¬å¹³

0.27

 earn

0.27

veal

0.26

angi

0.25

á»ĩp

0.25

morgan

0.24

engers

0.24

Activations Density 0.002%

ala

No Known Activations