INDEX

Explanations

public

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

uat

-0.26

pip

-0.25

åķĨåŃ¦éĻ¢

-0.24

åĲ¯ç¤º

-0.24

 Drill

-0.24

 comercial

-0.24

ä¹ħ

-0.23

ieber

-0.23

fill

-0.23

til

-0.23

POSITIVE LOGITS

ottes

0.27

 advoc

0.27

-choice

0.26

Ð°ÑĤÑĥÑĢ

0.26

aille

0.26

nock

0.25

å¤ĩä»½

0.25

åĬŀäºĭ

0.25

áº¯ng

0.24

_equiv

0.24

Activations Density 0.024%

public

No Comments

No Known Activations