© 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. 40907
    Prev
    Next
    INDEX
    Explanations

    comparison operators and symbols

    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
    åIJİèĢħ
    -0.08
    åĽŀ
    -0.07
    ych
    -0.07
    اÙħÙĬØ©
    -0.06
    æĸ°ä¸Ģ
    -0.06
    åĴĸåĸ±
    -0.06
    hui
    -0.06
    æİ»
    -0.06
    ontos
    -0.06
    erus
    -0.06
    POSITIVE LOGITS
     ±
    0.09
    ä¸Ĭä¸ĭ
    0.09
    ±
    0.09
     +-
    0.08
    å·¦åı³
    0.08
    åĽ´ç»ķ
    0.08
     +/-
    0.08
    æ½ľç§»é»ĺ
    0.08
    åīįåIJİ
    0.08
    .dev
    0.08
    Activations Density 0.081%

    No Known Activations