© 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. 45985
    Prev
    Next
    INDEX
    Explanations

    writings, documentation, articles

    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
     manufacture
    -0.08
    ÃģP
    -0.08
    对åħ¶çľŁå®ŀæĢ§è´Łè´£
    -0.07
    太éĥİ
    -0.07
    ä¸İä¼Ĺä¸įåIJĮçļĦ
    -0.07
    æĽ¾çĶ¨åIJį
    -0.07
    gge
    -0.07
    på
    -0.07
     Ingl
    -0.07
    ä½Ĩä¸įæĺ¯
    -0.07
    POSITIVE LOGITS
     countless
    0.08
    绪
    0.08
    类似éĹ®é¢ĺ
    0.07
     numerous
    0.07
    åīįèĮħ
    0.07
     تؤ
    0.07
    纷纷
    0.07
    à¹Ħà¸Ķà¹īà¹Ģลย
    0.07
    æľīè¿Ļæł·çļĦ
    0.07
     often
    0.07
    Activations Density 0.009%

    No Known Activations