© 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. 45200
    Prev
    Next
    INDEX
    Explanations

    numbers and mathematical symbols

    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
     Repar
    -0.09
    Ụ
    -0.08
    guer
    -0.08
    并ä¸įä¼ļ
    -0.07
     NotImplemented
    -0.07
    缴åij¼
    -0.07
     Ø´Ùĥ
    -0.07
    并ä¸įéľĢè¦ģ
    -0.07
    UTIL
    -0.07
    çīĪæĿĥæīĢæľī
    -0.07
    POSITIVE LOGITS
    éĢ¸
    0.07
    ering
    0.07
    _critical
    0.07
     critically
    0.07
     central
    0.06
    ä¸Ń央
    0.06
    èijĹåIJįçļĦ
    0.06
    åħ³æĢĢ
    0.06
    æī¬
    0.06
    V
    0.06
    Activations Density 0.003%

    No Known Activations