INDEX

Explanations

leading

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

HUD

-0.28

sdl

-0.26

zen

-0.26

 Oman

-0.25

bÃ¶

-0.25

ind

-0.25

_sdk

-0.25

éħįæĸ¹

-0.25

 constitution

-0.24

agen

-0.24

POSITIVE LOGITS

ç

0.26

kw

0.24

 superClass

0.24

çĤķ

0.24

Ð¸ÑĤÐµÐ»ÑĮÐ½

0.23

-angle

0.23

imbus

0.23

ä¸Ģè¶Ł

0.23

isVisible

0.23

æĵĤ

0.23

Activations Density 0.002%

leading

No Comments

No Known Activations