INDEX

Explanations

primarily

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

BOTTOM

-0.27

 SERIAL

-0.25

 bottom

-0.24

 repeatedly

-0.24

 BOTTOM

-0.24

pan

-0.23

icts

-0.23

 mare

-0.23

URRE

-0.23

emap

-0.23

POSITIVE LOGITS

fighter

0.28

çļĦæŃ¥ä¼Ĳ

0.26

stood

0.26

çļĦæĸ¹åĲĳ

0.25

aab

0.24

èµĦæľ¬å¸Ĥåľº

0.24

uze

0.24

USR

0.23

union

0.23

 Include

0.23

Activations Density 0.051%

primarily

No Comments

No Known Activations