INDEX

Explanations

code and documentation

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ILLA

-0.27

å¹¡

-0.24

illas

-0.24

mk

-0.24

æ¶Ī

-0.23

æ¹®

-0.23

 bracket

-0.23

*)

-0.23

apult

-0.23

vos

-0.23

POSITIVE LOGITS

loid

0.26

rides

0.25

è¦

0.24

umes

0.24

éľ¾

0.23

åªļ

0.23

exampleInput

0.23

æĮĩçĶ²

0.23

åĩºåħ¥

0.23

.slim

0.23

Activations Density 0.006%

code and documentation

No Comments

No Known Activations