INDEX

Explanations

Code and text formats

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_22.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.22.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

amb

-0.29

jk

-0.28

wf

-0.27

æ´¥

-0.26

æīįçŁ¥éģĵ

-0.25

Responder

-0.25

ä¹ŁçŁ¥éģĵ

-0.24

ANGER

-0.24

 witness

-0.24

èĨł

-0.24

POSITIVE LOGITS

nas

0.26

è½¬åĲĳ

0.26

stown

0.26

æĮº

0.26

 spins

0.24

ilename

0.24

ColorBrush

0.23

SupportedContent

0.23

tempts

0.23

 Smooth

0.23

Activations Density 0.005%

Code and text formats

No Known Activations