© 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. 15731
    Prev
    Next
    INDEX
    Explanations

    code and math 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
    VID
    -0.07
    eton
    -0.07
    èİ
    -0.07
    YLE
    -0.07
    ANEL
    -0.06
    åĭ¿æī°
    -0.06
    UND
    -0.06
    并å¤Ħ
    -0.06
    assa
    -0.06
    ä¸ŃåĽ½åħ±äº§åħļæĪIJç«ĭ
    -0.06
    POSITIVE LOGITS
    ather
    0.07
     faci
    0.07
    otics
    0.07
    ä»įåľ¨
    0.07
    okay
    0.07
    jum
    0.07
    ä¸įåIJĮæĦı
    0.06
    artz
    0.06
    atts
    0.06
    ç¨İè´¹
    0.06
    Activations Density 0.001%

    No Known Activations