© 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. 50643
    Prev
    Next
    INDEX
    Explanations

    complex numbers and analysis

    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
    à¸Ķย
    -0.09
    AndUpdate
    -0.08
    á»ĩp
    -0.08
    ypical
    -0.08
     plasti
    -0.07
    ä¸Ģå®ļçļĦ
    -0.07
    liste
    -0.07
    æģ¤
    -0.07
    OfMonth
    -0.07
    Ñģловно
    -0.07
    POSITIVE LOGITS
    udes
    0.08
    ä½łæ°¸è¿ľ
    0.07
    cape
    0.07
    -coded
    0.07
     entirety
    0.07
    æĪ·æĪ·
    0.07
    erto
    0.06
    ness
    0.06
    -val
    0.06
    سر
    0.06
    Activations Density 0.005%

    No Known Activations