© 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. 1041
    Prev
    Next
    INDEX
    Explanations

    place names

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

    No Comments

    Negative Logits
     America
    -24.13
    美国总统
    -22.88
     america
    -22.00
     american
    -21.63
    Philadelphia
    -21.63
    America
    -21.38
    American
    -21.00
     American
    -20.63
    美国人
    -20.63
    美国
    -20.50
    POSITIVE LOGITS
    钙
    16.75
     muscle
    16.38
    军人
    15.13
    mus
    15.06
    tensor
    15.00
    银行
    14.94
    肌肉
    14.50
    谱
    14.38
    肌
    14.25
     calcul
    14.13
    Activations Density 0.208%

    No Known Activations