INDEX

Explanations

hyphens

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

iously

-0.28

oka

-0.28

ONY

-0.28

zin

-0.27

heid

-0.26

INO

-0.25

yon

-0.25

ãģ¾ãģĹãģ¦

-0.25

etsk

-0.25

uppy

-0.24

POSITIVE LOGITS

oles

0.33

å·¡åĽŀ

0.28

setup

0.27

éĹªçĥģ

0.26

 tour

0.26

è´¯ç©¿

0.25

ä¸Ģçľ¼

0.25

_TEM

0.25

è¹Ī

0.25

 setup

0.25

Activations Density 0.222%

hyphens

No Comments

No Known Activations