INDEX

Explanations

code

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

recht

-0.30

 commission

-0.28

å§Ķæīĺ

-0.27

tables

-0.27

vie

-0.26

 intest

-0.26

ERICA

-0.26

 Chung

-0.25

 commissions

-0.25

åĩºèĩª

-0.25

POSITIVE LOGITS

äºĶåįĥ

0.28

Ð³Ð¾Ð´

0.27

ViewById

0.27

 pretend

0.26

é¼Ĳ

0.26

åıĻ

0.26

 ÑĢÐ°Ð²Ð½Ð¾

0.25

_ann

0.25

éĩįçĤ¹é¢ĨåŁŁ

0.25

 ÑģÑĤÐ°Ð»

0.24

Activations Density 0.001%

code

No Comments

No Known Activations