INDEX

Explanations

Article/entry introductions

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

.factory

-0.26

 kindly

-0.25

åľºåĿĩ

-0.25

gia

-0.25

rat

-0.24

 Pins

-0.24

_completion

-0.24

-sectional

-0.23

 asserting

-0.23

velt

-0.23

POSITIVE LOGITS

ymous

0.30

omon

0.30

(tm

0.27

 scare

0.27

erras

0.26

å³¤

0.25

iti

0.24

ÑģÐºÐ¾

0.24

ILLA

0.24

çļĦä¸Ģ

0.24

Activations Density 0.002%

Article/entry introductions

No Comments

No Known Activations