© 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. 1819
    Prev
    Next
    INDEX
    Explanations

    string

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

    No Comments

    Negative Logits
    字符串
    -42.25
     string
    -40.75
     STRING
    -37.50
     strings
    -36.75
    string
    -35.00
    strings
    -35.00
    STRING
    -34.50
     Strings
    -33.75
    Strings
    -33.50
     String
    -33.25
    POSITIVE LOGITS
     McCain
    16.63
    обор
    16.13
     Honda
    15.63
    Japanese
    15.19
     technical
    15.06
    technical
    15.06
    院
    14.94
     Nhật
    14.94
    党风
    14.69
    日本
    14.44
    Activations Density 0.084%

    No Known Activations