INDEX

Explanations

Institute

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

asto

-0.29

GRAM

-0.28

ä¸Ģå¾ĭ

-0.27

 kettle

-0.26

pson

-0.26

arming

-0.25

olib

-0.24

Ã¹

-0.24

:"

-0.24

 allegiance

-0.23

POSITIVE LOGITS

**↵

0.27

 accepted

0.27

ä¿ĿçķĻ

0.26

issa

0.25

 Corpor

0.25

ä¿İ

0.25

Mvc

0.24

Desk

0.24

å¾Īå¤ļäºº

0.24

desk

0.24

Activations Density 0.001%

Institute

No Comments

No Known Activations