INDEX

Explanations

Bol

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

fre

-0.30

å»¶ç»Ń

-0.29

-ons

-0.27

çķĮçļĦ

-0.27

fre

-0.27

à¸Ħà¸Ń

-0.27

bases

-0.27

Jeb

-0.26

esch

-0.26

 giá»Ľi

-0.25

POSITIVE LOGITS

å¯¹åŃ©åŃĲ

0.28

 foreground

0.27

åį´æĺ¯

0.25

å¾Ĺå¥½

0.24

wright

0.24

doch

0.24

TZ

0.24

æ¨µ

0.24

gorithm

0.24

ç¥ľ

0.23

Activations Density 0.002%

Bol

No Comments

No Known Activations