INDEX

Explanations

Japanese

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

Anth

-0.29

hoot

-0.25

anth

-0.25

Web

-0.25

awi

-0.24

é¡

-0.24

à°³

-0.24

Å©

-0.23

åį³å°Ĩ

-0.23

Web

-0.23

POSITIVE LOGITS

edis

0.30

 Hicks

0.28

 Galaxy

0.27

-serif

0.25

 Sense

0.25

oris

0.25

 swims

0.25

exels

0.25

 segregation

0.25

idis

0.24

Activations Density 0.020%

Japanese

No Comments

No Known Activations