© 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. 1909
    Prev
    Next
    INDEX
    Explanations

    say phone‑related words

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

    No Comments

    Negative Logits
    手机
    -36.75
    智能手机
    -34.50
     phone
    -31.13
     smartphone
    -30.38
     Smartphone
    -28.75
    phone
    -28.63
    _phone
    -28.00
    phones
    -27.63
    Phone
    -27.13
     phones
    -27.13
    POSITIVE LOGITS
    /ar
    15.75
    (cs
    15.75
    sigma
    15.63
     Beacon
    15.56
     Ar
    15.31
    仲裁
    15.00
    igs
    14.75
    Ax
    14.69
    igm
    14.56
     ley
    14.56
    Activations Density 0.078%

    No Known Activations