INDEX

Explanations

ellipses

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

åĴĮä¸ªäºº

-0.25

èģĶç½ĳ

-0.25

ambda

-0.24

å¸Ĳåı·

-0.24

cams

-0.24

 redund

-0.24

ãģıãģªãĤĬ

-0.23

æ¬¢è¿İ

-0.23

éĺ²æĬ¤

-0.23

bullet

-0.23

POSITIVE LOGITS

icum

0.31

.nodeName

0.29

ilton

0.28

ither

0.27

Complex

0.26

 Complex

0.26

.asarray

0.26

XO

0.25

 Ð¿Ð¾ÑģÐ»

0.25

_complex

0.24

Activations Density 0.021%

ellipses

No Comments

No Known Activations