© 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. 1436
    Prev
    Next
    INDEX
    Explanations

    sand

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

    No Comments

    Negative Logits
     sand
    -41.25
     sands
    -39.75
    沙
    -39.00
     SAND
    -37.75
     Sand
    -37.25
    砂
    -36.00
    Sand
    -34.25
     sandy
    -32.75
     Sands
    -32.75
    sand
    -28.50
    POSITIVE LOGITS
    教会
    18.25
     Te
    17.63
    .Te
    15.38
    /WebAPI
    14.50
    IO
    14.19
    licted
    14.13
    ipc
    14.13
    -te
    13.25
     Washington
    13.06
    电气
    13.06
    Activations Density 0.080%

    No Known Activations