© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15073
    Prev
    Next
    INDEX
    Explanations

    instruments

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

    No Comments

    Negative Logits
    itarian
    -16.75
    .Lib
    -16.50
    ighthouse
    -15.63
    _yield
    -15.56
    医学院
    -15.38
    场均
    -15.38
    税务局
    -15.25
    зе
    -15.00
    aqu
    -14.94
    integral
    -14.88
    POSITIVE LOGITS
    打入
    12.94
    TableRow
    12.13
     ass
    12.00
    럭
    11.63
    apps
    11.50
    hx
    11.25
    irk
    11.19
    댄
    11.00
    xy
    11.00
     vx
    10.94
    Activations Density 0.037%

    No Known Activations