© 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. 39072
    Prev
    Next
    INDEX
    Explanations

    definition and explanation

    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
    æİĴ
    -0.07
    ories
    -0.06
    ision
    -0.06
    verty
    -0.06
    çķ¢ç«Ł
    -0.06
    yne
    -0.06
    innen
    -0.06
    bulk
    -0.06
    ä¿¡æģ¯
    -0.06
    æ±Łåİ¿
    -0.06
    POSITIVE LOGITS
    اتÙģ
    0.07
    åĢ¾åŁİ
    0.07
    ä¸ģ
    0.07
    注åĨĮæŶéĹ´
    0.07
    azzi
    0.07
    azza
    0.07
    سÙĬر
    0.07
    åľĪçļĦ
    0.07
    licer
    0.07
    ringer
    0.07
    Activations Density 0.001%

    No Known Activations