INDEX

Explanations

I

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

æľīåĵªäºĽ

-0.27

ãģŀ

-0.26

åĵªäºĽ

-0.25

ivor

-0.24

 accounted

-0.24

åħ¨å®¶

-0.24

è¿Ļæī¹

-0.24

è±Ĩçĵ£

-0.24

EA

-0.23

 serge

-0.23

POSITIVE LOGITS

 Entry

0.26

Ð½ÑģÐºÐ¾Ð³Ð¾

0.26

entr

0.25

ä¸»ä½ĵè´£ä»»

0.24

 proper

0.24

æĸ°é²ľ

0.24

 Ð´ÐµÑıÑĤÐµÐ»ÑĮ

0.24

 repetition

0.23

 Organization

0.23

 ÑĢÐ°Ð·

0.23

Activations Density 0.011%

I

No Comments

No Known Activations