© 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. 14484
    Prev
    Next
    INDEX
    Explanations

    the

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

    No Comments

    Negative Logits
     jewish
    -17.88
    chod
    -17.50
    aptcha
    -17.00
    芝麻
    -17.00
    坚果
    -16.88
    珍珠
    -16.88
    Josh
    -16.88
     Jew
    -16.50
     Judaism
    -16.25
     CHRIST
    -16.25
    POSITIVE LOGITS
    £o
    15.94
    Fs
    15.19
    mland
    14.88
    yon
    14.56
    _KP
    14.50
    Ek
    14.44
    主城区
    14.38
    Fc
    14.31
    ,rp
    14.25
     Yao
    14.19
    Activations Density 0.059%

    No Known Activations