© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 48786
    Prev
    Next
    INDEX
    Explanations

    converting numerical data types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ertz
    -0.06
    åĨµ
    -0.06
    _iff
    -0.06
    éĺ¿æĭī伯
    -0.06
    åĨł
    -0.06
     åt
    -0.06
    istro
    -0.06
    æľĢæĺ¯
    -0.06
     zna
    -0.06
    ç»´å°Ķ
    -0.06
    POSITIVE LOGITS
     rall
    0.08
    åı£çļĦ
    0.08
    uary
    0.08
    itarian
    0.07
    pit
    0.07
    æ¯ıä¸Ģ天
    0.07
    Tau
    0.07
    shint
    0.07
    uar
    0.07
    fle
    0.07
    Activations Density 0.017%

    No Known Activations