© 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. 1007
    Prev
    Next
    INDEX
    Explanations

    say "Indic script characters"

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

    No Comments

    Negative Logits
    �
    -16.13
     Maduro
    -16.00
    婵
    -15.56
     Vanderbilt
    -15.50
     Greenwich
    -15.50
     VL
    -15.25
     Alabama
    -14.75
    哥伦比亚
    -14.69
     adidas
    -14.56
     ADA
    -14.44
    POSITIVE LOGITS
     PP
    40.25
     P
    39.75
    nP
    36.25
     getP
    35.75
     Pv
    35.75
    (P
    35.50
    PP
    35.25
    PIP
    34.50
    Ｐ
    34.25
    -P
    34.00
    Activations Density 0.099%

    No Known Activations

    This feature has no known activations.