© 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. 14340
    Prev
    Next
    INDEX
    Explanations

    code delimiters or special characters

    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
    åIJİæĦŁ
    -0.06
    eeee
    -0.06
    porn
    -0.06
    èº«åľ¨
    -0.06
    iguez
    -0.06
    åĽ¢åĽ¢
    -0.06
    身亡
    -0.06
     Rheinland
    -0.06
    ä½ĵéŃĦ
    -0.06
    ä¸įæĹ©
    -0.06
    POSITIVE LOGITS
    ä¸ĭåIJĮ
    0.10
    Ñģполни
    0.08
    丽ä¸Ŀ
    0.08
    egah
    0.08
    serializer
    0.07
    лаÑĢÑĭ
    0.07
    tus
    0.07
    ndo
    0.07
    èĭ±æĸĩåŃĹ
    0.07
    ashian
    0.07
    Activations Density 0.503%

    No Known Activations