© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14741
    Prev
    Next
    INDEX
    Explanations

    function arguments

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

    No Comments

    Negative Logits
    arms
    -18.63
     quotations
    -17.88
    horse
    -17.88
    Clip
    -17.63
    IFS
    -17.50
     Parenthood
    -17.50
    布
    -17.25
    Jos
    -17.25
     quotation
    -17.25
    brick
    -17.13
    POSITIVE LOGITS
    ieved
    12.56
     le
    12.06
    ual
    11.50
     Le
    11.19
    副总裁
    11.06
    待
    11.00
    mediate
    10.94
    有用的
    10.88
    修为
    10.81
    ison
    10.75
    Activations Density 0.021%

    No Known Activations