© 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. 13947
    Prev
    Next
    INDEX
    Explanations

    projection sequence

    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
    ÑĢем
    -0.08
    æ¦Ħ
    -0.08
    quit
    -0.07
    åīį段æŶéĹ´
    -0.07
    åįģäºĮæĮĩ
    -0.07
    æīĢ以çİ°åľ¨
    -0.07
     remix
    -0.07
    _FIND
    -0.07
    licit
    -0.07
    iker
    -0.07
    POSITIVE LOGITS
    对æīĢæľī
    0.14
    åľ¨æīĢæľī
    0.14
    åľ¨åIJĦç§į
    0.13
     ÙĦجÙħÙĬع
    0.12
    åľ¨åIJĦ个
    0.11
    æīĢæľī
    0.11
     across
    0.10
     forall
    0.10
    åľ¨ä¸įåIJĮ
    0.10
    ãģĻãģ¹ãģ¦ãģ®
    0.10
    Activations Density 0.069%

    No Known Activations