© 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. 17661
    Prev
    Next
    INDEX
    Explanations

    new sequence or related ideas

    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
    ilu
    -0.08
    è·¯éĢı
    -0.07
    heit
    -0.07
    eware
    -0.07
    ive
    -0.07
    æĦŁåĪ°éĿŀ常
    -0.07
    urz
    -0.07
    身çļĦ
    -0.07
    ersen
    -0.07
    常è§ĦçļĦ
    -0.07
    POSITIVE LOGITS
     new
    0.10
    [new
    0.10
    æĸ°çļĦ
    0.10
    æĸ°çļĦä¸Ģ
    0.09
     yeni
    0.09
    æĸ°å¢ŀ
    0.09
    æĸ°ãģĹãģĦ
    0.09
    (new
    0.09
    ,new
    0.09
    æĸ°å¢ŀäºĨ
    0.08
    Activations Density 0.002%

    No Known Activations