INDEX

Explanations

state

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_10.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.10.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

idia

-0.29

è¹Ī

-0.27

(Board

-0.26

inent

-0.26

serter

-0.25

ä¿®èº«

-0.25

/board

-0.25

ÑĪÐ°

-0.25

 curses

-0.25

icles

-0.24

POSITIVE LOGITS

Fix

0.30

 reap

0.26

ç¦»

0.25

 Editorial

0.25

à¹Īà¸²à¸¢

0.25

agem

0.24

æĭī

0.24

~↵↵

0.24

ornings

0.24

ÙħÙĤ

0.23

Activations Density 0.006%

state

No Comments

No Known Activations

state

No Comments

No Known Activations