© 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. 24240
    Prev
    Next
    INDEX
    Explanations

    review articles discuss

    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
    å®ŀéªĮ
    -0.09
    .test
    -0.08
    ¤íĹ
    -0.08
    çļĦå®ŀéªĮ
    -0.08
    å®ŀéªĮä¸Ń
    -0.08
     Antal
    -0.08
    ç«ŁçĦ¶
    -0.08
     experiment
    -0.08
    éªĮè¯ģ
    -0.08
     nghiá»ĩm
    -0.08
    POSITIVE LOGITS
    综述
    0.10
    /topics
    0.09
     overview
    0.09
     review
    0.08
    纲
    0.08
     reviews
    0.08
     summarizes
    0.08
    Reviewed
    0.08
    æıIJ纲
    0.08
    æ¦Ĥæĭ¬
    0.08
    Activations Density 0.528%

    No Known Activations