© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 947
    Prev
    Next
    INDEX
    Explanations

    say 萧

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

    No Comments

    Negative Logits
    igu
    -19.75
     PA
    -16.63
     OTA
    -16.50
    olem
    -16.38
    Türkiye
    -16.00
     NT
    -15.69
    OTA
    -15.50
     Juda
    -15.19
     JNI
    -14.81
     Jerusalem
    -14.75
    POSITIVE LOGITS
    萧
    72.50
     CS
    67.00
    CS
    62.50
    蕭
    62.00
     cs
    59.75
    (cs
    58.75
    	cs
    54.00
    cs
    51.75
    (Cs
    50.25
    /cs
    48.75
    Activations Density 0.037%

    No Known Activations