© 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. 7373
    Prev
    Next
    INDEX
    Explanations

    let or suppose

    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
     lequel
    -0.07
    åºĶäºĪ
    -0.07
    ï¸İ
    -0.06
    鲨
    -0.06
    åĴĮæݨ广
    -0.06
    ование
    -0.06
    anggal
    -0.06
    åľ¨äºĨä¸Ģèµ·
    -0.06
    оÑĢÑı
    -0.06
    ing
    -0.06
    POSITIVE LOGITS
    >window
    0.07
     Tij
    0.07
    erner
    0.07
    agin
    0.07
    åħ³æ³¨æĪij们
    0.07
     {}.
    0.07
     tepatnya
    0.07
    .ba
    0.07
    æĬĢæľ¯ä¸ĵä¸ļ
    0.07
    vero
    0.07
    Activations Density 0.018%

    No Known Activations