INDEX

Explanations

circuits and electronics

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

à¸¢à¸°

-0.28

_loading

-0.27

agger

-0.26

etta

-0.26

imson

-0.26

 loading

-0.26

istol

-0.25

morgan

-0.25

aped

-0.25

icket

-0.25

POSITIVE LOGITS

ç²¾

0.29

å®ĮåĸĦ

0.25

xm

0.25

ä½¿

0.25

ç¬¬åħŃ

0.24

iores

0.24

å¸ĮæľĽ

0.24

osit

0.24

 creo

0.23

hoot

0.23

Activations Density 0.020%

circuits and electronics

No Comments

No Known Activations