INDEX

Explanations

negative

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

è¿Ļå¯¹

-0.29

antom

-0.28

ÑĨÐ¸Ð°Ð»ÑĮÐ½Ð¾

-0.27

çļĦæĥħ

-0.26

è·µ

-0.25

yles

-0.24

 prow

-0.24

ä¸ºä¼ģä¸ļ

-0.24

 Purdue

-0.24

å®ŀä½ĵ

-0.24

POSITIVE LOGITS

éĨĴæĿ¥

0.25

_joint

0.25

Opening

0.25

[Unit

0.24

elerik

0.24

![

0.24

 ÐºÐ¾Ð½ÐºÑĥÑĢÑģ

0.24

æ¸ł

0.23

æı©

0.23

è¯¢

0.23

Activations Density 0.018%

negative

No Comments

No Known Activations