© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 2098
    Prev
    Next
    INDEX
    Explanations

    magnet

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

    No Comments

    Negative Logits
    註
    -18.75
     Deliver
    -18.13
    (util
    -17.63
    (Util
    -17.50
    Recursive
    -17.38
     delivering
    -17.13
    Wil
    -16.88
     ctx
    -16.75
    .Util
    -16.63
    	util
    -16.13
    POSITIVE LOGITS
     magnet
    57.00
     Magnet
    50.25
     magnets
    39.50
     Magn
    37.00
     mag
    34.75
     magn
    34.50
    磁
    34.00
    agnet
    33.25
    Mag
    33.00
     Mag
    32.75
    Activations Density 0.037%

    No Known Activations