© 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. 24188
    Prev
    Next
    INDEX
    Explanations

    diagrams, images, illustrations

    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
    åĢ¼
    -0.07
    kus
    -0.07
    åĢ¼æĺ¯
    -0.07
    usin
    -0.07
    åħ¶å®ĥçļĦ
    -0.07
     Edel
    -0.07
     minlength
    -0.07
    åħ·ä½ĵå¦Ĥä¸ĭ
    -0.07
    shima
    -0.07
    киÑģло
    -0.07
    POSITIVE LOGITS
    示æĦıåĽ¾
    0.09
     diagrams
    0.09
     diagram
    0.08
    åı¯æĥľ
    0.08
     Diagram
    0.08
    示æĦı
    0.08
    igel
    0.08
    Diagram
    0.07
    åĽ¾æĸĩ
    0.07
    幡
    0.07
    Activations Density 0.007%

    No Known Activations