© 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. 2663
    Prev
    Next
    INDEX
    Explanations

    author

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

    No Comments

    Negative Logits
    [strlen
    -16.00
    蛋白
    -15.88
     chips
    -14.50
     Regulation
    -14.50
    naments
    -14.31
     protein
    -13.94
    .Temp
    -13.56
     regulation
    -13.56
     watch
    -13.50
    ignon
    -13.25
    POSITIVE LOGITS
    笔者
    65.50
    筆
    47.50
    笔
    45.25
     writer
    40.25
    (writer
    36.00
     writers
    34.50
     pen
    34.50
    Pen
    33.75
    writer
    33.50
     Writer
    33.50
    Activations Density 0.087%

    No Known Activations