© 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. 2627
    Prev
    Next
    INDEX
    Explanations

    code tokens

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

    No Comments

    Negative Logits
    PDO
    -17.75
    单车
    -16.88
     Cake
    -16.63
     HttpServletRequest
    -16.00
     TOD
    -15.88
     CCD
    -15.63
     TLC
    -15.56
     Tulsa
    -15.31
    谠
    -15.13
     PDO
    -15.06
    POSITIVE LOGITS
     delt
    15.06
    .py
    14.44
    .splitext
    13.94
     py
    13.81
    ‎
    13.75
    pery
    13.69
     Franken
    13.63
    _packages
    13.50
     Py
    13.50
    .archive
    12.81
    Activations Density 0.098%

    No Known Activations