INDEX

Explanations

news articles

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

 actions

-0.28

 order

-0.27

actions

-0.26

 pair

-0.25

 easier

-0.25

nnen

-0.24

 shares

-0.24

eam

-0.24

op

-0.24

ayar

-0.24

POSITIVE LOGITS

ä¿±ä¹Ĳéĥ¨

0.31

ounder

0.27

duplicate

0.26

ÐºÐ»Ð¸

0.26

å¼ĥ

0.26

/Foundation

0.26

istr

0.24

losing

0.24

 lokal

0.24

 Those

0.23

Activations Density 5.225%

news articles

No Comments

No Known Activations