© 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. 45412
    Prev
    Next
    INDEX
    Explanations

    algebraic structures and mathematical notation

    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
    浪
    -0.07
    åŁ¼
    -0.07
    éļĪ
    -0.07
    PropertyValue
    -0.07
    éĿŀ常é«ĺ
    -0.06
    åĽŀ转
    -0.06
    abouts
    -0.06
    éļıåľ°
    -0.06
    çļĦè¿IJåĬ¨
    -0.06
    èĥ½åIJĥèĭ¦èĢIJåĬ³
    -0.06
    POSITIVE LOGITS
    éĽĨåIJĪ
    0.08
    仲
    0.08
    OfSize
    0.07
    illage
    0.07
    éĽĨä½ĵçļĦ
    0.07
    itr
    0.07
     empty
    0.07
     Kühlsch
    0.07
    поÑĩ
    0.07
    itis
    0.07
    Activations Density 0.010%

    No Known Activations