INDEX

Explanations

current times/world

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

åħ»

-0.27

ikki

-0.27

ÑĮÑİ

-0.26

jang

-0.26

ategies

-0.25

 ticks

-0.24

ä¸Ń

-0.24

éĩĮçļĦ

-0.24

acks

-0.24

å¼ĢæĿ¥

-0.24

POSITIVE LOGITS

OLER

0.29

çĺ¢

0.28

release

0.26

endum

0.26

ements

0.25

 Shotgun

0.25

 release

0.25

éĩĬæĶ¾

0.25

mun

0.24

iece

0.24

Activations Density 0.001%

current times/world

No Comments

No Known Activations