© 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. 14382
    Prev
    Next
    INDEX
    Explanations

    population numbers

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

    No Comments

    Negative Logits
    mn
    -20.38
    Mario
    -19.00
    uyen
    -18.88
    锰
    -18.50
     Mao
    -18.50
     millones
    -18.38
     Mae
    -18.38
    ilian
    -18.13
     Martins
    -18.13
    mart
    -18.00
    POSITIVE LOGITS
    tem
    17.38
     quat
    17.25
     GPI
    17.00
     Gim
    16.25
     qb
    16.25
    ATAB
    16.25
     GK
    16.13
    巴斯
    16.13
    atum
    16.00
     Peb
    15.94
    Activations Density 0.068%

    No Known Activations