INDEX

Explanations

morb

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

sam

-0.32

sav

-0.27

srv

-0.26

åĿļæŀľ

-0.26

lbl

-0.26

screen

-0.26

itted

-0.25

lease

-0.25

æĬĺ

-0.25

POSITIVE LOGITS

 biome

0.29

 Subject

0.26

æ¬²æľĽ

0.25

Deadline

0.25

å§Ķä¼ļ

0.25

æīĵäº¤éģĵ

0.25

Monkey

0.25

ç¼ºçĤ¹

0.24

naires

0.24

ç´¢èµĶ

0.24

Activations Density 6.243%

morb

No Known Activations