© 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. 14580
    Prev
    Next
    INDEX
    Explanations

    definite article

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

    No Comments

    Negative Logits
    _hashes
    -16.50
    _ARCHIVE
    -15.31
    MON
    -15.19
     HASH
    -14.81
    mdi
    -14.69
    DIC
    -14.63
    TOR
    -14.50
    agnitude
    -14.50
    mono
    -14.44
    射
    -14.31
    POSITIVE LOGITS
    欄
    16.13
    啜
    14.94
    閒
    14.88
    相亲
    14.31
    cname
    14.06
    周刊
    13.63
     tast
    13.38
    lv
    13.06
    周六
    12.88
     cname
    12.81
    Activations Density 0.053%

    No Known Activations