© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 12999
    Prev
    Next
    INDEX
    Explanations

    comparison operators with numbers/variables

    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
    ë²Į
    -0.07
    éĻ¤äºĨåľ¨
    -0.07
    éĻ¤äºĨ
    -0.07
    æĬ«
    -0.07
    ä»ĩ
    -0.07
     Salvini
    -0.07
    оÑĩе
    -0.07
    agine
    -0.06
    .populate
    -0.06
    'O
    -0.06
    POSITIVE LOGITS
    saf
    0.08
    гона
    0.08
    åIJ¬èµ·æĿ¥
    0.08
    _sess
    0.07
    ras
    0.07
    .separator
    0.07
    ïs
    0.07
    |array
    0.07
    æľ¬ç«ĻæīĢæľī
    0.07
    áĢ¾
    0.07
    Activations Density 0.004%

    No Known Activations