INDEX

Explanations

accurate

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_4.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.4.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

åĲĪãģĨ

-0.32

resenter

-0.28

coat

-0.26

_INITIALIZER

-0.26

 coat

-0.26

åħ»æĪĲ

-0.25

Õ¹

-0.25

covering

-0.25

uil

-0.24

Ã¤lt

-0.23

POSITIVE LOGITS

ç²¾åº¦

0.28

accur

0.27

aper

0.25

åĩĨç¡®æĢ§

0.25

 categor

0.25

UNE

0.25

 accur

0.25

 ÑģÑĦ

0.25

DNC

0.24

 Categories

0.24

Activations Density 0.047%

accurate

No Comments

No Known Activations