© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15126
    Prev
    Next
    INDEX
    Explanations

    numeric literals

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

    No Comments

    Negative Logits
    大厦
    -16.88
     орг
    -16.63
    PathComponent
    -16.63
    外国语
    -16.25
    图画
    -15.88
    shoot
    -15.81
    峪
    -15.63
    /Page
    -15.56
    登山
    -15.56
    pagina
    -15.50
    POSITIVE LOGITS
    apos
    15.25
    วก
    13.75
     π
    13.56
    e
    13.38
    :[[
    13.00
    .Counter
    12.94
    itos
    12.81
    anks
    12.81
     value
    12.63
    funcs
    12.63
    Activations Density 0.078%

    No Known Activations