© 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. 14209
    Prev
    Next
    INDEX
    Explanations

    say patent

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

    No Comments

    Negative Logits
    .cmd
    -16.75
    commands
    -16.63
    stress
    -16.25
    FUNC
    -16.25
    levator
    -16.13
    .Cmd
    -16.00
    eteria
    -15.81
    家庭教育
    -15.75
     cmdline
    -15.75
    \Command
    -15.44
    POSITIVE LOGITS
    专利
    35.00
     patent
    29.88
     patents
    28.25
    知识产权
    26.88
     Patent
    26.63
    pat
    26.38
    Pat
    25.88
     protection
    25.25
     Pat
    25.13
    PAT
    24.38
    Activations Density 0.211%

    No Known Activations