© 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. 2374
    Prev
    Next
    INDEX
    Explanations

    admin

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

    No Comments

    Negative Logits
    emons
    -16.13
     Arr
    -15.81
     arrangement
    -15.25
     phenomen
    -14.81
     segmentation
    -14.75
     Harr
    -14.63
     \'
    -14.56
    ij
    -14.50
    ynes
    -14.25
     demonstration
    -14.06
    POSITIVE LOGITS
     admin
    31.13
     config
    29.50
     doc
    27.00
     Admin
    25.63
    Admin
    24.75
     tech
    24.75
     admins
    24.50
    admin
    24.25
    (config
    24.13
     gen
    22.63
    Activations Density 0.033%

    No Known Activations