© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14935
    Prev
    Next
    INDEX
    Explanations

    citation number

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

    No Comments

    Negative Logits
    IVING
    -17.50
    dio
    -16.75
    ardon
    -16.25
    edBy
    -15.25
    @d
    -15.13
    当局
    -15.06
    一起来
    -14.75
    дет
    -14.69
    venida
    -14.69
    NING
    -14.69
    POSITIVE LOGITS
    anus
    16.63
    os
    15.25
    anal
    14.00
     Ros
    13.56
    FC
    13.44
     stick
    13.25
     Lancaster
    13.19
     gloves
    13.13
    KH
    13.06
    (car
    13.00
    Activations Density 0.034%

    No Known Activations