INDEX

Explanations

name

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

æ»¡

-0.28

æ»¿

-0.27

æĢĿæĥ³

-0.27

FUL

-0.26

ithe

-0.25

Pink

-0.25

æĢĿ

-0.24

çĶŁåŃĺ

-0.24

 View

-0.24

æ¦Ĥå¿µ

-0.23

POSITIVE LOGITS

ufacturer

0.25

ondo

0.25

ç¢į

0.25

è©Ī

0.25

decltype

0.25

unes

0.25

ryptography

0.24

agnet

0.24

 nipple

0.24

IGN

0.24

Activations Density 0.002%

name

No Comments

No Known Activations