© 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. 61559
    Prev
    Next
    INDEX
    Explanations

    computing terms

    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
    äs
    -0.07
    anto
    -0.07
    çŃ¹
    -0.06
    _namespace
    -0.06
    è¨Ĺ
    -0.06
    éģĵ
    -0.06
    kas
    -0.06
    ัà¸ģษ
    -0.06
    cho
    -0.06
    etz
    -0.06
    POSITIVE LOGITS
    ä¸Ģèĩ´çļĦ
    0.09
    ieszcz
    0.08
    ussian
    0.08
    ANGED
    0.07
    _WATCH
    0.07
    blatt
    0.07
    ÑĨева
    0.07
    é¡»çŁ¥
    0.07
    æĶ¾è¿ĩ
    0.07
    çļĦä¸Ģèĩ´æĢ§
    0.07
    Activations Density 0.001%

    No Known Activations