© 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. 14361
    Prev
    Next
    INDEX
    Explanations

    [1] => [9]

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

    No Comments

    Negative Logits
     Cav
    -16.13
    ف
    -16.13
    bow
    -15.50
    mes
    -14.88
    camp
    -14.75
    yat
    -14.31
    Al
    -14.19
    ldb
    -14.13
    ce
    -14.00
    owl
    -14.00
    POSITIVE LOGITS
     сто
    16.50
    １
    15.75
    uin
    15.00
    /cop
    13.94
     Barnes
    13.81
    ４
    13.56
    ngr
    13.44
    üst
    13.38
     towering
    13.31
    appings
    13.25
    Activations Density 0.061%

    No Known Activations