INDEX

Explanations

Questions and suggestions

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

gh

-0.33

åł´

-0.30

åľº

-0.29

gh

-0.28

rgba

-0.27

çļĦåĽŀçŃĶ

-0.27

åĽŀçŃĶ

-0.25

æĥħåĨµè¿Ľè¡Į

-0.25

å®ŀéĻħæĥħåĨµ

-0.25

pez

-0.25

POSITIVE LOGITS

æįĲçĮ®

0.27

_LINUX

0.26

abis

0.26

views

0.25

_foreign

0.24

inux

0.24

 dile

0.24

oxid

0.24

 Titanium

0.24

æĭĽèĤ¡

0.24

Activations Density 0.002%

Questions and suggestions

No Comments

No Known Activations