© 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. 47765
    Prev
    Next
    INDEX
    Explanations

    mathematical expression formatting

    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
    ¬
    -0.06
    porn
    -0.06
    zÅijd
    -0.06
    ebo
    -0.06
    ä¼
    -0.06
    odox
    -0.06
    éter
    -0.06
    å¤įå¼ı
    -0.06
    ŀ
    -0.06
    éħįç½®æĸ¹éĿ¢
    -0.06
    POSITIVE LOGITS
    gether
    0.09
    ulette
    0.08
     gäller
    0.07
    maal
    0.07
    ãĥ£
    0.07
    缮å½ķä¸Ģè§Ī
    0.07
    ritti
    0.07
    oley
    0.07
    ارÛĮ
    0.07
    ashes
    0.06
    Activations Density 0.003%

    No Known Activations