© 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. 1686
    Prev
    Next
    INDEX
    Explanations

    sulfate, selenite, silicate, titanate, phosphide, arsenate, selenide

    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
    åIJĿ
    -0.07
    _optimizer
    -0.07
    esti
    -0.07
    åºĦéķĩ
    -0.07
    Ø£ÙĬ
    -0.06
     ÐĿÐŁ
    -0.06
    æĸ°åĬłåĿ¡
    -0.06
    hatan
    -0.06
    éĤĥ
    -0.06
    lenme
    -0.06
    POSITIVE LOGITS
    ึà¸ĩ
    0.07
    angel
    0.07
    oxide
    0.07
    æĤ¨åı¯èĥ½
    0.07
     Worlds
    0.07
    rozen
    0.07
    ughter
    0.07
    ÙĪÙĨ
    0.07
    atom
    0.07
     Spells
    0.07
    Activations Density 0.028%

    No Known Activations