© 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. 10248
    Prev
    Next
    INDEX
    Explanations

    Taylor expansion series

    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
     QLD
    -0.07
    åĴ¬çīĻ
    -0.07
    ä¸Ĭä¸Ģå±Ĥ楼
    -0.07
    两份
    -0.06
     barley
    -0.06
     Coul
    -0.06
    å¤ļä¸Ģ份
    -0.06
    ç»·ç´§
    -0.06
    itet
    -0.06
     parale
    -0.06
    POSITIVE LOGITS
     expansions
    0.08
    oppins
    0.07
    åºı
    0.07
    稽
    0.07
    è°IJ
    0.07
    è¹Ń
    0.07
    åĿŀ
    0.07
     urs
    0.07
    dam
    0.07
    Cong
    0.07
    Activations Density 0.005%

    No Known Activations