© 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. 15912
    Prev
    Next
    INDEX
    Explanations

    laminoplast lancet refrigerators

    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
    ´
    -0.07
    oja
    -0.07
     dát
    -0.06
    åĿļæĮģ
    -0.06
    ิà¹Īà¸ĩ
    -0.06
    à¹Īà¸Ńà¸Ļ
    -0.06
    ucch
    -0.06
    à¸ļัà¸į
    -0.06
     [âĢ¦]
    -0.06
    selling
    -0.06
    POSITIVE LOGITS
    æĺ¯æĮĩåľ¨
    0.07
    æ·ĭæ¼ĵå°½
    0.07
    éŀŃçŃĸ
    0.06
    æī«æııä¸ĭæĸ¹äºĮç»´çłģ
    0.06
    æĪij们å°Ĩä¼ļ
    0.06
    uria
    0.06
    ITOR
    0.06
    antil
    0.06
    \_
    0.06
    ×ķ×ķת
    0.06
    Activations Density 0.003%

    No Known Activations