© 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. 15034
    Prev
    Next
    INDEX
    Explanations

    say route

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

    No Comments

    Negative Logits
    andez
    -15.63
    лож
    -15.50
    普查
    -15.13
    hoot
    -14.94
    追问
    -14.88
    白糖
    -14.81
     MLA
    -14.75
    ocoder
    -14.69
    (gl
    -14.38
    ughs
    -14.25
    POSITIVE LOGITS
    entr
    15.88
    道路
    15.31
    通道
    14.63
    咽喉
    14.31
     route
    14.31
     acesso
    14.19
    route
    14.19
     Route
    13.94
     Passage
    13.94
    车道
    13.75
    Activations Density 0.095%

    No Known Activations