INDEX

Explanations

indefinite article

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

Lo

-0.27

éĥ½è®¤ä¸º

-0.25

 accompanying

-0.25

èĦĨ

-0.25

Lo

-0.25

 Suite

-0.24

enco

-0.24

lo

-0.23

QUI

-0.23

erness

-0.23

POSITIVE LOGITS

ä¸ĩåĲ¨

0.27

é£İåı£

0.27

è¡ĮåĬ¨

0.25

icare

0.25

å¹´ä»¥ä¸Ĭ

0.25

åıįåĩ»

0.24

 garg

0.24

Magn

0.24

 dumping

0.24

æĸ¹

0.23

Activations Density 0.073%

indefinite article

No Comments

No Known Activations