© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15475
    Prev
    Next
    INDEX
    Explanations

    proper nouns

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AdminController
    -22.38
    控制器
    -20.25
     Controller
    -20.25
    Controllers
    -19.63
    rollo
    -19.50
    artial
    -19.38
    (Controller
    -19.25
     controllers
    -19.25
    Controller
    -19.13
    _CONTROLLER
    -19.00
    POSITIVE LOGITS
    钻石
    18.88
    鲨
    18.25
     Aleppo
    18.25
    珙
    17.75
    Apollo
    17.25
     Sierra
    16.88
     Everest
    16.88
     treeNode
    16.63
     Apollo
    16.63
    桐
    16.38
    Activations Density 0.410%

    No Known Activations