© 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. 1547
    Prev
    Next
    INDEX
    Explanations

    say 文献

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

    No Comments

    Negative Logits
    Java
    -16.38
     BMW
    -15.88
    MC
    -15.19
    均匀
    -15.06
     Java
    -15.00
    uniform
    -14.94
    语言
    -14.94
     weather
    -14.88
    itled
    -14.81
     Cair
    -14.81
    POSITIVE LOGITS
    文献
    18.63
    鲜花
    16.63
     Ark
    15.44
     HID
    15.31
    文
    15.25
    migration
    15.06
    lobe
    14.94
    膳食
    14.81
    Diagnostic
    14.75
     школ
    14.63
    Activations Density 0.111%

    No Known Activations