© 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. 14487
    Prev
    Next
    INDEX
    Explanations

    [,] => [,]

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

    No Comments

    Negative Logits
     Saud
    -16.50
    DataExchange
    -15.75
    物质
    -15.63
    orrent
    -15.56
     COMMENTS
    -15.56
    _vk
    -15.25
    _Des
    -15.25
    ipt
    -15.19
    oods
    -15.19
    -hand
    -15.00
    POSITIVE LOGITS
     internally
    15.00
    fé
    14.81
    digit
    13.69
    yang
    13.63
    ||(
    13.56
     mamm
    13.13
     fé
    13.06
    偃
    13.00
    车内
    12.81
    蚊
    12.81
    Activations Density 0.087%

    No Known Activations