© 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. 64499
    Prev
    Next
    INDEX
    Explanations

    submerged or immersed in water

    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
    ativamente
    -0.09
    ativas
    -0.08
    atives
    -0.08
    é¹ıé£ŀ
    -0.08
    ativo
    -0.08
    oriously
    -0.08
    retto
    -0.07
     aven
    -0.07
    atera
    -0.07
    ounces
    -0.07
    POSITIVE LOGITS
    æĪĸéĥ¨åĪĨ
    0.09
    深度
    0.09
    å¾Īæ·±
    0.08
     sâu
    0.08
    æĽ´æ·±
    0.08
     dive
    0.08
    ลึà¸ģ
    0.08
    åŁĭ
    0.08
     deeper
    0.08
    æľĢæ·±
    0.08
    Activations Density 0.027%

    No Known Activations