© 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. 22218
    Prev
    Next
    INDEX
    Explanations

    particle Hamiltonian

    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
    åĢĴäºĨ
    -0.08
    GetPosition
    -0.08
    å°Ķé¡¿
    -0.07
    è°ĥåĪ¶
    -0.07
    ãĥ¼ãĥŀ
    -0.07
    вой
    -0.07
    ç§ģæĪ¿
    -0.07
     ÑģÑĤи
    -0.07
    -Mart
    -0.07
    %p
    -0.07
    POSITIVE LOGITS
    anta
    0.08
     consum
    0.07
    æĸ°æĶ¿
    0.06
    _generic
    0.06
    æľĢç®ĢåįķçļĦ
    0.06
    æ±½
    0.06
    ç®Ģ书
    0.06
    çļĦæľĢå°ı
    0.06
     Momentum
    0.06
     구ìĦ±
    0.06
    Activations Density 0.001%

    No Known Activations