© 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. 14478
    Prev
    Next
    INDEX
    Explanations

    say justify

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

    No Comments

    Negative Logits
    vore
    -16.88
     "),↵
    -15.88
     '~
    -15.13
    就好
    -14.75
    ivor
    -14.69
     deed
    -14.56
    为止
    -14.44
    上门
    -14.31
    塵
    -14.19
    ych
    -14.13
    POSITIVE LOGITS
     reap
    14.94
    _nat
    14.38
    nt
    14.19
    sess
    13.06
     comics
    12.56
    潇
    12.50
    asper
    12.44
    ética
    12.31
     experiments
    12.25
    ampa
    12.25
    Activations Density 0.004%

    No Known Activations