© 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. 1976
    Prev
    Next
    INDEX
    Explanations

    [nav] => [navicular]

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

    No Comments

    Negative Logits
    创新
    -26.88
    TV
    -26.50
     TV
    -26.25
    -TV
    -25.38
    _tv
    -25.38
    tv
    -25.13
     tv
    -25.13
    _TV
    -24.88
     innovation
    -23.63
    创新发展
    -23.50
    POSITIVE LOGITS
    肌肉
    24.75
     muscle
    21.50
    肌
    18.88
     muscles
    18.63
    罗马
    18.25
     Muscle
    18.13
    mus
    17.38
    字体
    16.75
    土壤
    16.63
     Roman
    15.88
    Activations Density 0.305%

    No Known Activations