© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15352
    Prev
    Next
    INDEX
    Explanations

    ship names

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

    No Comments

    Negative Logits
    ropy
    -20.00
    控制系统
    -16.38
    rome
    -16.13
    mars
    -16.13
    cats
    -15.94
    olph
    -15.94
    _api
    -15.75
    sse
    -15.38
     controllers
    -15.31
    json
    -15.19
    POSITIVE LOGITS
    豉
    14.06
     soften
    13.75
    Priority
    13.00
     multit
    12.94
     dipl
    12.88
    Junior
    12.88
    -ranking
    12.81
     decency
    12.75
    减速
    12.38
     мяг
    12.31
    Activations Density 0.088%

    No Known Activations