© 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. 27665
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and identifiers

    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
    uret
    -0.07
    请åIJĦä½į
    -0.07
    imbus
    -0.07
    sit
    -0.07
    yle
    -0.06
    éķ¿çĶŁ
    -0.06
    üssel
    -0.06
    çª
    -0.06
    aret
    -0.06
    ä¸Ī夫
    -0.06
    POSITIVE LOGITS
    kert
    0.08
    qua
    0.07
    ä¼ĺ
    0.07
    .cf
    0.07
    åĦª
    0.07
    viz
    0.07
    ứng
    0.07
    çĸ¯çĭĤçļĦ
    0.07
    åį³åľ¨
    0.07
    çĭĻ
    0.07
    Activations Density 0.030%

    No Known Activations