© 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. 18977
    Prev
    Next
    INDEX
    Explanations

    successive items, variables, patients

    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
    istry
    -0.08
    åĴĮç»´çĶŁç´ł
    -0.08
    ero
    -0.07
    adat
    -0.07
    åĴĮ红
    -0.07
    asia
    -0.06
    ège
    -0.06
     mojo
    -0.06
    ISTRY
    -0.06
    ongyang
    -0.06
    POSITIVE LOGITS
    ively
    0.10
    èĢĮæĿ¥çļĦ
    0.09
    aneously
    0.09
    大大å°ıå°ıçļĦ
    0.08
    áĥĿáĥij
    0.08
    LY
    0.08
    emente
    0.08
    iating
    0.07
    ãĢħ
    0.07
     successive
    0.07
    Activations Density 0.019%

    No Known Activations