INDEX

Explanations

scientific/mathematical texts

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

-po

-0.27

Pvt

-0.27

undi

-0.27

èĭĭ

-0.27

ej

-0.26

å¡Ķ

-0.26

çļĩ

-0.25

çĽ´

-0.25

åĸĤ

-0.25

æ¶£

-0.24

POSITIVE LOGITS

çŃļ

0.30

DL

0.29

adium

0.27

_FN

0.27

Ð´ÑĥÐ¼

0.26

ç©¹

0.24

á»ĵn

0.24

arium

0.24

Fn

0.24

Grade

0.24

Activations Density 0.008%

scientific/mathematical texts

No Comments

No Known Activations