© 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. 4342
    Prev
    Next
    INDEX
    Explanations

    defined by formula or equation

    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
    åIJĮä¸Ĭ
    -0.07
    hov
    -0.07
    äºĨæĮĩ
    -0.07
    ÅĤow
    -0.07
    emat
    -0.07
    rab
    -0.07
    aget
    -0.07
    EMAT
    -0.06
    -org
    -0.06
    èijĨ
    -0.06
    POSITIVE LOGITS
    å¾Ĺæ°´
    0.07
    åħ¬å¼ı
    0.07
    <form
    0.07
    ä¸Ńè·¯
    0.07
     formula
    0.07
    å¼Ģåı£è¯´éģĵ
    0.07
    å¾Ĺä¸Ģ
    0.07
    ippi
    0.06
    formula
    0.06
     relationship
    0.06
    Activations Density 0.036%

    No Known Activations