INDEX

Explanations

of

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

æĭĸ

-0.28

æīķãģĦ

-0.27

rou

-0.27

riad

-0.27

htag

-0.26

äºĨ

-0.26

ä¹ĺ

-0.25

tent

-0.25

åı·

-0.25

 Birthday

-0.24

POSITIVE LOGITS

è®¤æ¸ħ

0.27

-windows

0.25

.getBoundingClientRect

0.24

æİ´

0.24

Gra

0.23

inct

0.23

 bipartisan

0.23

éĮ¾

0.23

.toJSON

0.23

é«ĳ

0.23

Activations Density 1.204%

of

No Comments

No Known Activations