© 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. 34524
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions or questions

    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
    èĢħ为
    -0.08
    迪äºļ
    -0.08
    ijat
    -0.08
    wali
    -0.08
     Monsters
    -0.08
    æľ¬æĬ¥
    -0.08
    evol
    -0.08
    ias
    -0.08
    ä¸İæĸ¹æ³ķ
    -0.08
    esia
    -0.08
    POSITIVE LOGITS
    åIJĴ
    0.06
    jons
    0.06
    çŀĴ
    0.06
    èijĹ
    0.06
    sv
    0.06
    cardo
    0.06
    ŀ
    0.06
    åį±
    0.06
    éķ¿æ²³
    0.05
    duction
    0.05
    Activations Density 0.519%

    No Known Activations