INDEX

Explanations

words ending in ative/atory/itory/ptive/ulatory

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

omat

-0.27

pressive

-0.26

erman

-0.26

çŁŃæľŁåĨħ

-0.25

ãģľ

-0.25

 concrete

-0.24

åıĹ

-0.24

é³³

-0.24

å¿«

-0.23

xFFFF

-0.23

POSITIVE LOGITS

anness

0.29

 shaved

0.28

 shaving

0.27

 Razor

0.26

 shave

0.26

 independence

0.25

 cellpadding

0.25

æ²¡åķ¥

0.25

ebin

0.25

çĤ¹äºĨ

0.24

Activations Density 0.611%

words ending in ative/atory/itory/ptive/ulatory

No Comments

No Known Activations