© 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. 31409
    Prev
    Next
    INDEX
    Explanations

    electromyographic abnormalities

    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
    èī²åĪĹ
    -0.09
    almaz
    -0.09
    ÏĥÏħ
    -0.08
    íĢĦ
    -0.08
    íĽ¨
    -0.07
    >Hello
    -0.07
    ÑģовеÑģÑĤ
    -0.07
    ë¸
    -0.07
    зоÑĢÑĥ
    -0.07
    itters
    -0.07
    POSITIVE LOGITS
    åĴĮè¡Į为
    0.07
     ÙĨØ®
    0.07
    er
    0.07
    åį°è¯ģ
    0.07
    ®
    0.06
    åħ¸åŀĭçļĦ
    0.06
    ym
    0.06
     change
    0.06
    èªĮ
    0.06
    ehr
    0.06
    Activations Density 0.017%

    No Known Activations