INDEX

Explanations

Japanese topics

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

aise

-0.26

æĿľ

-0.25

inger

-0.24

iated

-0.24

abbage

-0.24

legt

-0.24

haps

-0.24

aises

-0.23

cheiden

-0.23

æĺİ

-0.23

POSITIVE LOGITS

åĽ½æĥħ

0.28

 boot

0.28

world

0.27

ç®¡çĲĨä¸Ńå¿ĥ

0.27

Ymd

0.27

orient

0.27

boot

0.26

 webs

0.25

 numel

0.25

èĭįçĻ½

0.25

Activations Density 0.032%

Japanese topics

No Comments

No Known Activations