© 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. 16227
    Prev
    Next
    INDEX
    Explanations

    CH and chemical formulas

    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
    .yy
    -0.08
    XHR
    -0.07
    ly
    -0.07
    жаÑħ
    -0.07
    äºİè¡Į
    -0.07
    ès
    -0.07
    eni
    -0.07
    ifix
    -0.07
    íݸ
    -0.07
    ifi
    -0.07
    POSITIVE LOGITS
    ë¡Ŀ
    0.07
    vern
    0.07
    åIJĪåIJĮæŶ
    0.06
    urgo
    0.06
    ofday
    0.06
    缨
    0.06
    omber
    0.06
    ATORY
    0.06
    æĹ¥æĬ¥ç¤¾
    0.06
    à¸IJาà¸Ļ
    0.06
    Activations Density 0.007%

    No Known Activations