© 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. 14686
    Prev
    Next
    INDEX
    Explanations

    large-number units

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

    No Comments

    Negative Logits
    mel
    -17.50
    tein
    -17.50
    布朗
    -16.38
    terrain
    -15.88
    trs
    -15.69
    tid
    -15.31
    tournament
    -15.31
    bm
    -14.75
    Transaction
    -14.63
    دان
    -14.63
    POSITIVE LOGITS
     COPYING
    15.50
    rü
    15.25
     gốc
    15.00
     Powered
    14.94
     lawsuits
    13.88
    .createStatement
    13.81
    ilver
    13.81
    Powered
    13.75
     economy
    13.69
    ServiceProvider
    13.63
    Activations Density 0.025%

    No Known Activations