© 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. 24629
    Prev
    Next
    INDEX
    Explanations

    numerical sequences

    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
     RegExp
    -0.07
     Falls
    -0.07
     Curt
    -0.06
    áĭ«
    -0.06
    عة
    -0.06
     balance
    -0.06
    æĬĬä¸Ģ个
    -0.06
    åĴĮ家éķ¿
    -0.06
     Rob
    -0.06
    atar
    -0.06
    POSITIVE LOGITS
    çŁ¥éŁ³
    0.09
    phin
    0.08
    types
    0.08
    osten
    0.08
    è³Ĭ
    0.08
    éķ¿æ²³
    0.07
    ibly
    0.07
    ÄĽ
    0.07
    reis
    0.07
    åŀĭåĴĮ
    0.07
    Activations Density 0.284%

    No Known Activations