© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 655
    Prev
    Next
    INDEX
    Explanations

    [token] => [,]

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

    No Comments

    Negative Logits
    南京市
    -17.38
    堪
    -16.88
    sing
    -16.63
    onas
    -15.81
    boat
    -15.31
     Mexico
    -15.13
    ở
    -14.81
    бол
    -14.63
    杭州市
    -14.44
    ils
    -13.81
    POSITIVE LOGITS
    黑龙
    18.75
    yi
    18.13
     SAND
    18.00
    石油化工
    17.50
    Firestore
    17.38
     Fighters
    17.25
    珠海
    17.25
     Ai
    17.13
    魔兽
    16.50
    白斑
    16.50
    Activations Density 0.273%

    No Known Activations