© 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. 2955
    Prev
    Next
    INDEX
    Explanations

    say mill

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

    No Comments

    Negative Logits
    _descriptor
    -17.75
    descriptor
    -17.00
    pets
    -17.00
    Descriptors
    -17.00
    consts
    -16.75
    .ctx
    -16.75
    宠物
    -16.50
     Cond
    -16.38
    .det
    -16.13
     Resets
    -16.13
    POSITIVE LOGITS
     mill
    79.50
     Mill
    75.00
    mill
    71.50
    Mill
    70.50
     MILL
    61.00
     mills
    59.50
     mil
    46.75
    千
    46.75
     Mil
    45.75
     milling
    44.25
    Activations Density 0.167%

    No Known Activations