© 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. 14005
    Prev
    Next
    INDEX
    Explanations

    say expedition

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

    No Comments

    Negative Logits
     getInput
    -17.63
    InputDialog
    -17.63
    开盘
    -17.50
    小店
    -17.38
    产能
    -17.00
    旗舰店
    -16.63
    店面
    -16.25
    店
    -15.88
    整治
    -15.75
    议事
    -15.50
    POSITIVE LOGITS
     expedition
    26.13
    探险
    24.00
     Expedition
    24.00
     explorer
    23.00
     Exped
    22.75
     journeys
    22.75
    地图
    22.13
    旅途
    21.38
    旅行
    21.13
     voyage
    20.88
    Activations Density 0.889%

    No Known Activations