INDEX

Explanations

commas

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

ç§°ä¹ĭ

-0.28

åĩłåĪĨéĴŁ

-0.27

disposing

-0.27

æĹ¥æ¶Īæģ¯

-0.26

Ä±nt

-0.26

HomeController

-0.26

AFF

-0.25

æĪ·

-0.25

 tastes

-0.24

 tuyáº¿n

-0.24

POSITIVE LOGITS

å¤įæ´»

0.26

oy

0.26

oyo

0.25

áº§m

0.24

 Antar

0.24

ï¼ĮåĪĻ

0.24

SuppressWarnings

0.24

fir

0.24

å¿ĻçĿĢ

0.23

ensation

0.23

Activations Density 0.001%

commas

No Comments

No Known Activations