© 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. 46656
    Prev
    Next
    INDEX
    Explanations

    fractions in algebraic expressions

    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
    tre
    -0.07
    ç¬ij
    -0.07
    忧
    -0.06
    !:
    -0.06
    çħŀ
    -0.06
    ç¬ijçļĦ
    -0.06
    tores
    -0.06
    arus
    -0.06
    ith
    -0.06
     sát
    -0.06
    POSITIVE LOGITS
    à®Łà¯Ī
    0.07
    è¡ĮåĬ¨ä¸Ń
    0.07
    áĢ
    0.07
    erson
    0.07
    çļĦèĥĮåIJİ
    0.07
    _HINT
    0.07
    ÑĥÑģÑĤа
    0.07
    estelle
    0.07
    çİĩ为
    0.07
    ookies
    0.07
    Activations Density 0.006%

    No Known Activations