INDEX

Explanations

varied snippets

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

fffffff

-0.28

èº«åĲİ

-0.27

 miracles

-0.26

ãĤį

-0.25

èº«

-0.25

 Alternate

-0.24

classified

-0.24

lick

-0.24

('/',

-0.24

é£İéĻ©

-0.24

POSITIVE LOGITS

æįĲåĬ©

0.28

 sort

0.26

çļĦä¸Ģæ¬¾

0.26

æ¥¼ä¸»

0.25

å°ıç¼ĸä¸Ģèµ·

0.25

Bone

0.25

toc

0.25

Ð±ÑĢÐ°

0.24

 EXEMPLARY

0.24

sort

0.24

Activations Density 0.103%

varied snippets

No Comments

No Known Activations