© 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. 2650
    Prev
    Next
    INDEX
    Explanations

    say mand words

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

    No Comments

    Negative Logits
    .cur
    -17.00
    det
    -16.38
    =num
    -16.25
    cur
    -16.13
    util
    -16.00
    (det
    -16.00
    pres
    -15.56
    num
    -15.50
    (gen
    -15.19
     cur
    -15.13
    POSITIVE LOGITS
     Mand
    53.25
     mand
    46.75
    mand
    42.75
    MAND
    32.50
     mandate
    31.38
     mandates
    27.00
     mandated
    18.00
    .Cmd
    17.75
     Mandal
    17.25
     cmd
    16.63
    Activations Density 0.065%

    No Known Activations