© 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. 42426
    Prev
    Next
    INDEX
    Explanations

    that can

    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
    ¹Ħ
    -0.07
    å¤Ħ女
    -0.07
    åıĪå¤ļ
    -0.07
    ä¸įéĻIJäºİ
    -0.07
    utu
    -0.07
    ntax
    -0.07
    æĢİä¹Īå¤ĦçIJĨ
    -0.07
    dock
    -0.07
    ä¸įå®ĮçļĦ
    -0.07
    asco
    -0.06
    POSITIVE LOGITS
     réellement
    0.07
    å®ŀéĻħéľĢè¦ģ
    0.07
    èĥ½è¢«
    0.07
     effettivamente
    0.06
    称å¾Ĺä¸Ĭ
    0.06
    /topics
    0.06
     najczÄĻÅĽciej
    0.06
    sembl
    0.06
    aios
    0.06
    ارÙĩ
    0.06
    Activations Density 0.132%

    No Known Activations