© 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. 10784
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and linear algebra

    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
    è¿ĪæŃ¥
    -0.07
    มูล
    -0.07
    çļĦæĶ¿æ²»
    -0.07
    ScreenWidth
    -0.07
    emy
    -0.07
    umbed
    -0.07
    缺ä¸Ģ
    -0.07
     Crossing
    -0.07
    è¿ĪåIJij
    -0.06
    خر
    -0.06
    POSITIVE LOGITS
    æĬĬ人
    0.08
    jana
    0.07
    alter
    0.07
     mahal
    0.07
    _exchange
    0.07
    交æį¢
    0.07
    orda
    0.07
    ä¸İåħ±
    0.07
     cocos
    0.07
    оек
    0.07
    Activations Density 0.007%

    No Known Activations