© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1468
    Prev
    Next
    INDEX
    Explanations

    [alf] => [alfalfa]

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

    No Comments

    Negative Logits
    DF
    -30.13
     SF
    -29.50
    _SF
    -29.25
     coffee
    -28.88
     DF
    -28.63
     CF
    -27.00
     BF
    -27.00
    _sf
    -26.88
    SF
    -26.38
    	sf
    -26.38
    POSITIVE LOGITS
    -port
    17.00
     port
    15.38
    ounter
    15.31
     Mus
    15.25
     Musk
    14.94
    onom
    14.69
    ref
    14.63
    数码
    14.63
    (port
    14.56
    Mus
    14.50
    Activations Density 0.383%

    No Known Activations