© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14075
    Prev
    Next
    INDEX
    Explanations

    [proton] => [pump]

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

    No Comments

    Negative Logits
    模型
    -36.75
     models
    -35.00
     model
    -32.50
     Models
    -31.38
    model
    -31.25
    MODEL
    -30.88
     MODEL
    -30.88
    -model
    -30.00
    emodel
    -29.50
    models
    -29.13
    POSITIVE LOGITS
    财产
    18.13
     Property
    17.75
     property
    17.63
     administrations
    16.75
     решения
    16.50
    .solution
    16.25
     rozwiąz
    16.13
     solution
    16.00
    搬家
    15.75
     solución
    15.75
    Activations Density 0.838%

    No Known Activations