© 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. 17321
    Prev
    Next
    INDEX
    Explanations

    code syntax and structure

    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
    Ù°
    -0.08
    werten
    -0.07
    çĪĨ
    -0.07
    inders
    -0.07
    upe
    -0.06
    ì·¨
    -0.06
    wab
    -0.06
    ackt
    -0.06
     Fabrizio
    -0.06
    âĢİ
    -0.06
    POSITIVE LOGITS
    iany
    0.08
    æIJľç´¢çĽ¸åħ³èµĦæĸĻ
    0.08
    Lorem
    0.08
    çĪ±æĺ¯
    0.08
    ç»Ŀåľ°
    0.07
    éĥ¨çº§
    0.07
    å±ĤéĿ¢ä¸Ĭ
    0.07
     ãĢĮ
    0.07
    anya
    0.07
    ADE
    0.07
    Activations Density 0.004%

    No Known Activations