INDEX

Explanations

OK

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

æĹłåĬĽ

-0.29

Ø¨Ø®

-0.27

ug

-0.26

ÑĢÐµÐ²

-0.26

éĻįæ¸©

-0.25

é©¬åĬĽ

-0.25

ä¹ıåĬĽ

-0.25

boom

-0.24

vero

-0.24

Ð°ÑĨÐ¸Ð¸

-0.24

POSITIVE LOGITS

rapped

0.29

 deepest

0.27

gli

0.27

leur

0.26

lhs

0.25

çļĦåģļæ³ķ

0.25

lhs

0.25

reader

0.25

çº¢çº¿

0.24

 halfway

0.24

Activations Density 0.008%

OK

No Comments

No Known Activations