© 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. 1260
    Prev
    Next
    INDEX
    Explanations

    [di] => [Diwali]

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

    No Comments

    Negative Logits
     Di
    -63.00
    Di
    -60.25
     di
    -57.75
    di
    -53.50
    (di
    -52.50
    -di
    -52.00
    _di
    -52.00
    .di
    -50.00
    .Di
    -49.25
     DI
    -48.75
    POSITIVE LOGITS
    中俄
    17.63
    vat
    15.56
     Bris
    14.81
    俄
    14.81
    顺丰
    14.38
    Stamp
    14.00
    RLF
    13.88
     Stamp
    13.56
    盐
    13.50
    纳斯
    13.50
    Activations Density 0.070%

    No Known Activations