INDEX

Explanations

Citations

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

åĵĳ

-0.28

lename

-0.28

 Face

-0.28

éĿ¢éĥ¨

-0.27

,eg

-0.27

 poly

-0.27

æĪĲä¸ºä¸ŃåĽ½

-0.26

mens

-0.26

åıįä¹ĭ

-0.26

åĪ©çĶ¨çİĩ

-0.25

POSITIVE LOGITS

oz

0.30

 mechan

0.27

 scalar

0.26

(*)

0.26

 Pearson

0.25

 Randolph

0.25

 Redistribution

0.25

 distr

0.25

æĬĹæ°§åĮĸ

0.24

åĿĩåĮĢ

0.24

Activations Density 0.012%

Citations

No Comments

No Known Activations