© 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. 28080
    Prev
    Next
    INDEX
    Explanations

    quantum-classical correspondence and optics

    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
     redefine
    -0.07
    宣
    -0.07
    åĪĩç£ĭ
    -0.07
    åĪĿè¡·
    -0.07
    çµ®
    -0.06
     ÑĩÑĥгÑĥ
    -0.06
    èĤ¥å¤§
    -0.06
    寸
    -0.06
    溶解
    -0.06
     grate
    -0.06
    POSITIVE LOGITS
     semiclass
    0.11
     semiclassical
    0.08
    abat
    0.08
    临è¿ij
    0.08
     Brill
    0.08
     локали
    0.08
    é¢Ħè¨Ģ
    0.08
    голо
    0.08
    ouri
    0.08
    ê»
    0.08
    Activations Density 0.004%

    No Known Activations