INDEX

Explanations

introduced

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

urm

-0.34

æĭĽ

-0.31

.directive

-0.27

åŁ¹åħ»

-0.26

äºĮæīĭ

-0.25

åįļæĸĩ

-0.25

æĸĩåĮĸéģĹäº§

-0.25

å¯ĦãģĽ

-0.25

 JOIN

-0.24

ç¢İçīĩ

-0.24

POSITIVE LOGITS

 blunt

0.29

sburg

0.29

tors

0.27

 stepping

0.26

 grads

0.25

æ¨ĺ

0.25

ç§ģèĩª

0.25

STEP

0.24

enko

0.24

éĩįä¸Ń

0.24

Activations Density 0.015%

introduced

No Comments

No Known Activations