INDEX

Explanations

radiation

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_32.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.32.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

onis

-0.30

ies

-0.28

ç°¿

-0.27

ins

-0.26

pins

-0.26

èĴ¸

-0.26

 REPL

-0.26

 Pist

-0.25

 absolutely

-0.25

ç»Ŀå¯¹

-0.25

POSITIVE LOGITS

 COMPONENT

0.29

 component

0.28

PathComponent

0.28

åįģåħŃæĿ¡

0.27

component

0.27

 Component

0.26

ä¸Ģç»ı

0.26

æĸ«

0.25

_component

0.25

flow

0.25

Activations Density 0.001%

radiation

No Comments

No Known Activations