INDEX

Explanations

institutions/age

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_27.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.27.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

isors

-0.29

å°±æĺ¯è¿Ļæł·

-0.27

iesel

-0.27

practice

-0.26

processable

-0.26

ç¥ŀè¯Ŀ

-0.25

Thr

-0.24

ä¾Ľç»Ļä¾§

-0.24

 billions

-0.24

æīĵæ³ķ

-0.23

POSITIVE LOGITS

æİ§åĪ¶

0.26

 University

0.26

age

0.25

è¯¥æł¡

0.24

University

0.24

st

0.24

å±ĭ

0.24

åŁ¹è®Ń

0.24

åĵģåĳ³

0.24

aged

0.24

Activations Density 0.016%

institutions/age

No Comments

No Known Activations