© 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. 62006
    Prev
    Next
    INDEX
    Explanations

    license and copyright statements

    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
    佼佼
    -0.08
    èce
    -0.07
    дÑĢе
    -0.07
    ëĭĪëĭ¤
    -0.07
    noinspection
    -0.07
    RelativeTo
    -0.07
     Setia
    -0.07
    æĶ¿åºľåĴĮ
    -0.07
    mage
    -0.07
    .relative
    -0.07
    POSITIVE LOGITS
    ç»ıéĶĢ
    0.07
     Gow
    0.06
    aro
    0.06
    reek
    0.06
    éron
    0.06
     Feinstein
    0.06
    รร
    0.06
    ×ķ×Ĵ
    0.06
    æµij身
    0.06
    Ó©ÑĢ
    0.06
    Activations Density 2.954%

    No Known Activations