© 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. 31220
    Prev
    Next
    INDEX
    Explanations

    symplectic manifold

    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
    é¦Ļè¾£
    -0.07
    æģ©æĢ¨
    -0.07
    جار
    -0.07
    trand
    -0.07
    æĸ¹ä¾¿å¿«æį·
    -0.06
     Somma
    -0.06
    bsp
    -0.06
     schr
    -0.06
    æĶ»çł´
    -0.06
     عÙĨÙĩا
    -0.06
    POSITIVE LOGITS
    纽
    0.09
    ç¼Ķ
    0.08
    ä¸įåŃķ
    0.08
    ift
    0.07
    -blind
    0.07
    kowski
    0.07
    ieli
    0.07
    èī²åĪĹ
    0.07
    mir
    0.07
    ctic
    0.07
    Activations Density 0.004%

    No Known Activations