INDEX

Explanations

Consecutive/straight

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_20.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.20.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

ines

-0.30

=-=-=-=-

-0.26

ophobia

-0.25

ymous

-0.25

è¾Ļ

-0.25

æī©å®¹

-0.24

è¿İ

-0.24

æĥĬäºº

-0.24

iners

-0.24

rost

-0.24

POSITIVE LOGITS

à¤ŀ

0.27

Jet

0.25

itional

0.25

 laten

0.25

nor

0.25

 activity

0.25

èĢ½

0.25

AREN

0.24

åıĪè¢«

0.24

åĵº

0.24

Activations Density 3.226%

Consecutive/straight

No Known Activations