© 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. 28358
    Prev
    Next
    INDEX
    Explanations

    frac to {

    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
    utch
    -0.07
    umba
    -0.07
     ׼×IJ
    -0.06
    zcze
    -0.06
    oten
    -0.06
    itus
    -0.06
    交æĬķ
    -0.06
    onga
    -0.06
     [--
    -0.06
    umbu
    -0.06
    POSITIVE LOGITS
    èIJ½åľ¨äºĨ
    0.07
    éĻ¤äºĨåľ¨
    0.07
    èµŀ
    0.07
    elper
    0.07
    unity
    0.07
     ÙĨÙı
    0.07
    apol
    0.07
    obile
    0.07
    ober
    0.06
    åľ¨ä¸įåIJĮçļĦ
    0.06
    Activations Density 0.008%

    No Known Activations