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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 16156
    Prev
    Next
    INDEX
    Explanations

    [sea] => [sea]

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

    No Comments

    Negative Logits
     Hamp
    -17.88
     depos
    -17.63
     Depos
    -16.50
    ��
    -15.75
    pit
    -15.50
    复
    -15.38
    oteca
    -15.25
    开发建设
    -14.94
    -holder
    -14.88
    _titles
    -14.88
    POSITIVE LOGITS
    LEV
    18.88
    loor
    17.63
    urface
    17.63
     leveled
    17.63
     level
    17.50
     LEVEL
    16.88
     Level
    16.63
    (levels
    15.81
    LOOR
    15.69
    level
    15.63
    Activations Density 0.026%

    No Known Activations