© 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. 2837
    Prev
    Next
    INDEX
    Explanations

    Pompeo, Guarantee, Error

    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
    ingo
    -0.08
    çĿĢçī©
    -0.07
    _",
    -0.07
    åIJĮä¸Ĭ
    -0.07
    "",
    -0.07
    há
    -0.07
    antara
    -0.06
    è§Ĵ度åĩºåıij
    -0.06
    ÑĥÑīе
    -0.06
    argin
    -0.06
    POSITIVE LOGITS
    apo
    0.07
     Avg
    0.07
    enstr
    0.06
    ffer
    0.06
    umat
    0.06
     coli
    0.06
    èĴĤæĸ¯
    0.06
     sih
    0.06
     strugg
    0.06
    uby
    0.06
    Activations Density 0.001%

    No Known Activations