© 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. 18705
    Prev
    Next
    INDEX
    Explanations

    etc. and other similar abbreviations

    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
    tó
    -0.07
    elin
    -0.07
    igo
    -0.07
    ystal
    -0.07
    ä¸ĢçĤ¹çļĦ
    -0.07
    éĵ®
    -0.07
    vÄĽ
    -0.07
    .dimensions
    -0.07
    ç»Ńè´¹
    -0.07
    èIJ½ä¸ĭ
    -0.07
    POSITIVE LOGITS
     etc
    0.08
     usw
    0.07
    èĭ
    0.07
    å¾Ģ
    0.07
    æģ¬
    0.07
    æ³¾
    0.07
    ness
    0.07
     ÙĪغÙĬرÙĩا
    0.06
    ancara
    0.06
     mond
    0.06
    Activations Density 0.085%

    No Known Activations