© 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. 8628
    Prev
    Next
    INDEX
    Explanations

    cycle decomposition

    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
    AYER
    -0.08
    auce
    -0.07
    жек
    -0.07
    ä¸Ģæīĭ
    -0.07
    æľīæīĢ
    -0.07
    åŁ¼
    -0.07
    برا
    -0.07
    oslav
    -0.07
    èµŀè¿ĩ
    -0.07
    OUNDS
    -0.07
    POSITIVE LOGITS
    äf
    0.08
    coration
    0.07
    æĬĺ
    0.06
     normalized
    0.06
    åįłåħ¬åı¸
    0.06
    angu
    0.06
    yt
    0.06
    áf
    0.06
    æĮĩæłĩ
    0.06
    说ä¸įåĩº
    0.06
    Activations Density 0.038%

    No Known Activations