INDEX

Explanations

to

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

jong

-0.30

ï¼ļ</

-0.28

è¿ĩäºĨ

-0.27

 join

-0.27

çĽ®åīįå·²

-0.26

ancell

-0.25

Hog

-0.25

ucker

-0.25

æīĵåį¡

-0.24

junction

-0.24

POSITIVE LOGITS

MODE

0.27

_probe

0.25

å·¥ä½ľå²Ĺä½į

0.25

olan

0.25

 onRequest

0.24

é¹Ľ

0.24

KEN

0.24

 definit

0.23

èĬ±çĶŁ

0.23

Ð»ÑĥÑĪ

0.23

Activations Density 0.010%

to

No Comments

No Known Activations