© 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. 48731
    Prev
    Next
    INDEX
    Explanations

    formed or composed of

    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
    ¯
    -0.08
    为æĤ¨æݨèįIJ
    -0.07
    身æīĭ
    -0.07
    zÃŃ
    -0.07
     gär
    -0.07
    并éĩį
    -0.07
    áĢ¯
    -0.07
    quia
    -0.07
    amedi
    -0.06
    è¿ĩçĶŁæĹ¥
    -0.06
    POSITIVE LOGITS
    举æĸ¹
    0.07
    äk
    0.07
     mainly
    0.07
    çļĦçī¹çĤ¹æĺ¯
    0.07
     respectively
    0.06
    Õ¡Õ½
    0.06
    ä¸ŀ
    0.06
    minating
    0.06
    лаÑģ
    0.06
    /show
    0.06
    Activations Density 0.408%

    No Known Activations