© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 42267
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas and programming code

    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
    ัà¸ģ
    -0.06
    ä¸įä¸Ģå®ļ
    -0.06
    olla
    -0.06
    åºĶçĶ¨åŀĭ
    -0.06
     subscript
    -0.06
    辦
    -0.06
    ä¸Ģå®ļçļĦ
    -0.06
    ä¸ĢèĪ¬éľĢè¦ģ
    -0.06
    éĴ°
    -0.06
     Summer
    -0.06
    POSITIVE LOGITS
    ewriter
    0.07
    天å°Ĭ
    0.07
    OUSE
    0.07
    _GUI
    0.07
    alty
    0.07
    idge
    0.07
    jong
    0.06
    è®©æĽ´å¤ļçļĦ
    0.06
     Lars
    0.06
    uguay
    0.06
    Activations Density 0.004%

    No Known Activations