© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3-1.7B
    3. 26-LLAMASCOPE-2-LORSA-16K-K64
    4. 751
    Prev
    Next
    INDEX
    Explanations

    routing

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

    No Comments

    Negative Logits
    游艇
    -21.75
     Bethlehem
    -19.38
    枪
    -18.63
    VIN
    -18.38
     Essen
    -17.63
    船上
    -17.50
    海盗
    -17.50
     vodka
    -17.50
     aure
    -17.25
    邮轮
    -17.25
    POSITIVE LOGITS
    路由
    34.75
     routing
    31.63
     routes
    30.00
     Route
    29.00
     Routes
    28.88
     Routing
    28.63
     route
    28.50
    _route
    28.13
    Route
    27.88
     router
    27.00
    Activations Density 0.046%

    No Known Activations