© 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. 14867
    Prev
    Next
    INDEX
    Explanations

    [number] => [number]

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

    No Comments

    Negative Logits
    蝌
    -20.63
    中关
    -19.38
    onica
    -18.88
    .CreateInstance
    -17.00
    ец
    -16.88
    itzer
    -16.75
     Tyson
    -16.63
     тек
    -16.63
    olley
    -16.63
    izon
    -16.38
    POSITIVE LOGITS
    麟
    15.31
    ارات
    15.06
    下达
    13.88
    戌
    13.75
    年以来
    13.44
    _spinner
    13.31
    侑
    13.19
    omat
    13.06
    贵族
    12.75
    nak
    12.69
    Activations Density 0.001%

    No Known Activations