© 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. 28971
    Prev
    Next
    INDEX
    Explanations

    Roman numerals and citations

    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
    /cop
    -0.07
    ´Ī
    -0.07
    ernel
    -0.07
     Hearts
    -0.06
     nargs
    -0.06
    ollen
    -0.06
    å±±ä¸Ń
    -0.06
    DRAW
    -0.06
    .*(
    -0.06
    üste
    -0.06
    POSITIVE LOGITS
    illa
    0.07
    ç»Ń
    0.06
    rey
    0.06
    çºĮ
    0.06
     bÃłn
    0.06
    Ã¼ÅŁ
    0.06
    æķĽ
    0.06
    çıĢ
    0.06
    æĸ
    0.06
    omot
    0.06
    Activations Density 0.056%

    No Known Activations