© 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. 30764
    Prev
    Next
    INDEX
    Explanations

    training data, examples, experiments

    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
    ECT
    -0.07
    æ»¡çľ¼
    -0.06
    awi
    -0.06
    init
    -0.06
    å§ĭèĩ³
    -0.06
     dar
    -0.06
    ect
    -0.06
    çĭ¬ç§Ģ
    -0.06
    è¦ģåIJĥ
    -0.06
    antin
    -0.06
    POSITIVE LOGITS
    çļĦ模å¼ı
    0.08
    ç»ıéªĮ
    0.08
    aines
    0.08
    模å¼ı
    0.08
    ::::::::
    0.08
    adro
    0.07
     demais
    0.07
    åĴĮ建设
    0.07
    heimer
    0.07
    patterns
    0.07
    Activations Density 0.012%

    No Known Activations