© 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. 32986
    Prev
    Next
    INDEX
    Explanations

    numbers or symbols followed by words

    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
    é»Ħè±Ĩ
    -0.07
    aine
    -0.07
    è°Īç¬ij
    -0.07
    wujud
    -0.07
    AMED
    -0.07
     apprec
    -0.07
    ause
    -0.07
    شد
    -0.07
    好象
    -0.07
    湿äºĨ
    -0.07
    POSITIVE LOGITS
    ovsky
    0.08
    åºı
    0.07
    urah
    0.07
    uzion
    0.07
    ä¸įåı¯
    0.07
    éĻµ
    0.07
    éĩĮç¨ĭ
    0.06
    zell
    0.06
    ComputedStyle
    0.06
    æ·³
    0.06
    Activations Density 0.015%

    No Known Activations