© 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. 1386
    Prev
    Next
    INDEX
    Explanations

    [console] => [console]

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

    No Comments

    Negative Logits
    Console
    -29.63
    console
    -29.38
     console
    -29.38
     Console
    -28.38
    (Console
    -27.50
    (console
    -27.25
    -console
    -27.00
    _console
    -26.38
    .console
    -24.50
    _CONSOLE
    -24.50
    POSITIVE LOGITS
    玩耍
    18.00
    arters
    17.50
    AI
    17.50
     pi
    17.50
    pi
    17.13
     пи
    17.00
    AMY
    16.75
    atoi
    16.63
    пи
    16.63
    artin
    16.50
    Activations Density 0.152%

    No Known Activations