© 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. 14713
    Prev
    Next
    INDEX
    Explanations

    say numbers

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

    No Comments

    Negative Logits
    trys
    -17.38
    cá
    -17.13
     Goth
    -17.13
    kus
    -16.88
    walls
    -16.88
    (Build
    -16.38
    quier
    -16.38
    uest
    -16.38
    ęd
    -16.13
    èle
    -16.00
    POSITIVE LOGITS
    _diag
    15.38
     diag
    14.69
    lan
    13.94
    ランド
    13.19
    科学发展
    13.06
    diag
    12.88
     diagonal
    12.81
     penal
    12.75
     constant
    12.69
    -di
    12.63
    Activations Density 0.052%

    No Known Activations