© 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. 18102
    Prev
    Next
    INDEX
    Explanations

    motion and flow dynamics

    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
     dá»ĵi
    -0.09
    å§Ķ
    -0.09
     Moraes
    -0.09
    缮çŀª
    -0.09
    ISTI
    -0.08
     Setia
    -0.08
    kke
    -0.08
    oteles
    -0.08
    ặn
    -0.08
    ilos
    -0.08
    POSITIVE LOGITS
    åıijçĶŁåľ¨
    0.09
    åıijçĶŁäºİ
    0.08
    è¿IJåĬ¨
    0.08
     confined
    0.08
     motion
    0.08
     regulated
    0.07
     occurring
    0.07
     happening
    0.07
     characterized
    0.07
    è¿IJåĬ¨åĴĮ
    0.07
    Activations Density 0.007%

    No Known Activations