© 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. 2762
    Prev
    Next
    INDEX
    Explanations

    patent

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

    No Comments

    Negative Logits
     coord
    -16.88
     battles
    -15.75
     unloaded
    -15.19
     serv
    -14.88
    cur
    -14.81
    角色
    -14.56
    (cur
    -14.38
    的角色
    -14.31
     dim
    -14.19
    .removeChild
    -14.13
    POSITIVE LOGITS
     patent
    69.50
    专利
    68.50
     Patent
    65.50
     patents
    59.50
    Pat
    47.00
     patented
    45.50
    (pat
    44.00
    pat
    42.25
     Pat
    41.00
    发明专利
    40.75
    Activations Density 0.082%

    No Known Activations