© 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. 1785
    Prev
    Next
    INDEX
    Explanations

    atomic

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

    No Comments

    Negative Logits
    原子
    -45.75
     atom
    -41.25
     Atom
    -40.25
     atomic
    -39.25
     atoms
    -38.00
    Atom
    -38.00
    ATOM
    -37.75
     Atomic
    -37.50
    atom
    -36.00
    _atom
    -35.50
    POSITIVE LOGITS
     Gunn
    18.75
    山东
    17.00
     Gun
    15.19
    闽
    14.31
    edin
    14.31
    Ed
    14.25
    福建
    14.19
     Gand
    13.94
    illa
    13.69
    山东省
    13.63
    Activations Density 0.048%

    No Known Activations