INDEX

Explanations

software testing and modification

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

åĲİèĢħ

-0.29

å¹¶ä¸İ

-0.29

ä¸»å¯¼

-0.28

.Vertex

-0.27

locks

-0.27

é¦ĸå¸Ń

-0.27

TypeEnum

-0.26

ä¸»åĬĽåĨĽ

-0.26

Wei

-0.26

ElementType

-0.25

POSITIVE LOGITS

æįŁ

0.29

ÑģÐºÐ¾Ðµ

0.29

ç¼¸

0.27

æŃ¤æĹ¶

0.27

 altern

0.27

 spoil

0.26

åı¯èĥ½åĩºçİ°

0.26

crast

0.25

çŀ¬éĹ´

0.25

éĤĳ

0.25

Activations Density 0.784%

software testing and modification

No Comments

No Known Activations