INDEX

Explanations

questions and answers

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

*</

-0.25

-dom

-0.25

å¥Ħ

-0.24

 rebate

-0.24

 Powers

-0.24

ÂŃi

-0.24

gul

-0.24

panse

-0.24

à¹ģà¸Ń

-0.24

avg

-0.23

POSITIVE LOGITS

lip

0.27

ph

0.26

ph

0.25

èĮĥåĽ´åĨħ

0.24

çļĦä¾ĭåŃĲ

0.24

ç»

0.24

æŁ¥æĺİ

0.24

 harmless

0.24

ByExample

0.24

æµģæ°´

0.24

Activations Density 0.080%

questions and answers

No Comments

No Known Activations