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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1044
    Prev
    Next
    INDEX
    Explanations

    ingestion warnings

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

    No Comments

    Negative Logits
     engagement
    -41.25
     engaged
    -38.75
     engage
    -38.75
     Engagement
    -38.75
     engaging
    -37.75
     Eng
    -37.50
     engages
    -37.00
    eng
    -36.25
    Eng
    -34.25
     engagements
    -32.25
    POSITIVE LOGITS
    闱
    16.63
    书籍
    15.81
    书店
    15.50
     DECL
    15.38
    RARY
    15.38
    -books
    15.13
    书
    14.50
     Leia
    13.94
    MATRIX
    13.94
    Lİ
    13.75
    Activations Density 0.576%

    No Known Activations