INDEX

Explanations

delegation of power

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

(ERR

-0.27

readOnly

-0.26

keyboard

-0.26

antis

-0.26

 destin

-0.26

ä»ĸè¡¨ç¤º

-0.25

æİ§åĪ¶ç³»ç»Ł

-0.25

è¾¹çķĮ

-0.25

åĩı

-0.24

 tripod

-0.24

POSITIVE LOGITS

ipse

0.30

ä¹³ä¸ļ

0.30

[::-

0.28

åıĭåĸĦ

0.28

 coins

0.26

ä¸Ńçº§

0.26

enny

0.26

[{"

0.25

åŁĭ

0.25

 Superior

0.25

Activations Density 0.002%

delegation of power

No Comments

No Known Activations