© 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. 49990
    Prev
    Next
    INDEX
    Explanations

    silver

    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
    аÑĤ
    -0.08
    ÑģÑı
    -0.08
    gether
    -0.08
    hle
    -0.08
    оÑĢо
    -0.08
    nable
    -0.07
    ï¸ı
    -0.07
    erc
    -0.07
    åIJģ
    -0.07
    ä¸ŃåĽ½å®¶
    -0.07
    POSITIVE LOGITS
    vÄĽd
    0.08
    kut
    0.08
    epis
    0.08
    apore
    0.07
    ierto
    0.07
    æĢ»ç½²
    0.07
    à¬
    0.07
    åĴĮéĩij
    0.07
    ä¸ĵç§ijåŃ¦æł¡
    0.07
    azz
    0.07
    Activations Density 0.011%

    No Known Activations