INDEX

Explanations

Thank

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¨İçİĩ

-0.28

 faces

-0.26

zman

-0.26

å¼Ģåĩº

-0.26

 IllegalAccessException

-0.25

keley

-0.25

æ²¦

-0.24

oui

-0.24

æĻºåķĨ

-0.24

oper

-0.23

POSITIVE LOGITS

Specification

0.27

 Copp

0.25

 stap

0.25

ancell

0.25

å»Ĭ

0.25

 Reserved

0.24

rome

0.24

 leaving

0.23

Reservation

0.23

 há»Ļ

0.23

Activations Density 0.006%

Thank

No Comments

No Known Activations