© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 940
    Prev
    Next
    INDEX
    Explanations

    say pox

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

    No Comments

    Negative Logits
    单车
    -24.50
    南宁市
    -22.13
    车队
    -21.25
     Gst
    -20.13
     Greenland
    -19.38
     glacier
    -19.38
     glaciers
    -19.13
     Lug
    -19.13
    getRepository
    -18.88
    transport
    -18.38
    POSITIVE LOGITS
     po
    15.75
    ups
    14.88
     av
    14.75
    痘
    14.56
     vacc
    13.75
    桓
    13.69
    AFX
    13.69
     avi
    13.63
     skin
    13.38
     HP
    13.38
    Activations Density 0.022%

    No Known Activations