© 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. 16272
    Prev
    Next
    INDEX
    Explanations

    chemical elements

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

    No Comments

    Negative Logits
    奧
    -47.25
    奥
    -45.75
    -O
    -45.50
     OA
    -43.00
     OM
    -42.50
    /O
    -42.25
     OC
    -42.25
    -o
    -41.25
    _O
    -41.25
     OV
    -40.75
    POSITIVE LOGITS
    endon
    14.38
    endas
    14.13
    ilon
    13.69
    enden
    13.31
    蕨
    13.19
    .Suppress
    12.94
    Thunk
    12.81
    镞
    12.56
     fern
    12.56
    bolt
    12.56
    Activations Density 3.978%

    No Known Activations