© 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. 27455
    Prev
    Next
    INDEX
    Explanations

    calculus differentials and time intervals

    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
    åľ°ä¸Ĭ
    -0.08
    estand
    -0.07
    ernet
    -0.07
     pard
    -0.07
     suite
    -0.07
    eyer
    -0.06
    suite
    -0.06
    ä¸Ŀä¸Ŀ
    -0.06
    ró
    -0.06
    æķĪåĬĽ
    -0.06
    POSITIVE LOGITS
    _cum
    0.08
    èĵ¬
    0.08
    ç©į
    0.07
     acumul
    0.07
    累积
    0.07
    otime
    0.07
    TOT
    0.07
    åĬłæĸ¯
    0.07
    Cum
    0.07
    cum
    0.07
    Activations Density 0.002%

    No Known Activations