© 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. 14270
    Prev
    Next
    INDEX
    Explanations

    say "symbol"

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

    No Comments

    Negative Logits
    .mouse
    -17.00
    帮助企业
    -17.00
    网络营销
    -17.00
    发送
    -16.88
     Sen
    -16.63
    sent
    -16.50
     mice
    -16.38
    鼠标
    -16.38
    Mouse
    -16.38
     mouse
    -16.38
    POSITIVE LOGITS
    Symbol
    25.00
    -symbol
    24.75
    _symbol
    24.50
     symbols
    24.25
     symbol
    24.00
    ymbol
    24.00
    symbols
    23.88
    (Symbol
    23.88
    SYM
    23.88
     Symbol
    23.63
    Activations Density 0.184%

    No Known Activations