© 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. 14596
    Prev
    Next
    INDEX
    Explanations

    say places

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

    No Comments

    Negative Logits
    雠
    -13.81
     copyright
    -11.75
    ञ
    -11.63
    -md
    -11.44
    uos
    -11.06
    igure
    -10.94
     mau
    -10.88
    -.
    -10.88
    ѐ
    -10.81
    ทย
    -10.75
    POSITIVE LOGITS
    中国政府
    20.00
    当地政府
    18.75
    cks
    18.75
    南京市
    17.75
    elsey
    17.63
    李先生
    17.63
    市委书记
    17.63
    şi
    17.50
    Province
    17.50
    cker
    17.25
    Activations Density 0.223%

    No Known Activations