© 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. 37852
    Prev
    Next
    INDEX
    Explanations

    differential equations speed acceleration

    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
     Voyage
    -0.07
    褶
    -0.07
    zare
    -0.07
    æĬĺ
    -0.07
    ICollection
    -0.07
    QueryString
    -0.07
    (?:
    -0.07
    à¹ģà¸ķะ
    -0.07
    ãĥªãĥ³ãĤ°
    -0.06
    åĴĮçIJĨ解
    -0.06
    POSITIVE LOGITS
     acceler
    0.10
    éĢŁçİĩ
    0.09
     propel
    0.09
    åĬłéĢŁåº¦
    0.09
     propulsion
    0.09
     acceleration
    0.09
    æİ¨è¿Ľ
    0.08
     Rates
    0.08
     rates
    0.08
     rate
    0.08
    Activations Density 0.009%

    No Known Activations