© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1729
    Prev
    Next
    INDEX
    Explanations

    air

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

    No Comments

    Negative Logits
     AIR
    -36.75
     air
    -34.25
     Air
    -33.75
    AIR
    -33.50
    Air
    -33.25
    空气
    -31.38
    _air
    -31.00
    -air
    -30.38
    .air
    -29.75
     aire
    -27.63
    POSITIVE LOGITS
    盐
    15.75
    β
    15.69
     beta
    15.50
     Beta
    15.44
     β
    15.44
    蛋白
    15.31
    耶稣
    15.06
     Script
    15.00
    钙
    14.81
    ucs
    14.63
    Activations Density 0.094%

    No Known Activations