© 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. 22260
    Prev
    Next
    INDEX
    Explanations

    mathematical algebra and code constructs

    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
     vector
    -0.07
    ueling
    -0.07
    .vector
    -0.07
    æ³³æ±ł
    -0.06
     iconName
    -0.06
     vectors
    -0.06
    Tank
    -0.06
    çŁ¢éĩı
    -0.06
    éŀĺ
    -0.06
     Safari
    -0.06
    POSITIVE LOGITS
    -module
    0.08
     маÑĤÑĢи
    0.08
    å¤ļåŃĶ
    0.08
    ç«ĭ足
    0.08
     Ames
    0.08
    å¡Į
    0.07
     matriz
    0.07
    娲
    0.07
    äºĶèī²
    0.07
    åĿįå¡Į
    0.07
    Activations Density 0.036%

    No Known Activations