INDEX

Explanations

core

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

continued

-0.27

requestData

-0.25

&(

-0.24

 Network

-0.24

 continues

-0.24

MMC

-0.24

ç»§ç»Ń

-0.24

Network

-0.24

 Networks

-0.24

 continued

-0.24

POSITIVE LOGITS

veal

0.28

æīĵçĲĥ

0.28

è¹Ī

0.26

ÄĻÅ¼

0.26

åīĮ

0.25

 trial

0.25

_scal

0.24

roscope

0.24

ãĥ¼ãĤ¸

0.24

 implicitly

0.24

Activations Density 0.059%

core

No Comments

No Known Activations