© 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. 16930
    Prev
    Next
    INDEX
    Explanations

    vendor services

    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
    icine
    -0.08
    ä¸ģ
    -0.07
    ÑĤков
    -0.07
    .addObserver
    -0.07
    å·´æĸ¯
    -0.07
    龸éģĵ
    -0.07
    icin
    -0.07
    -labelledby
    -0.07
    obby
    -0.07
    OTS
    -0.07
    POSITIVE LOGITS
    åĴĮçĶŁäº§
    0.07
    onan
    0.07
    onar
    0.07
    ajer
    0.06
    ä¸İç»ıæµİ
    0.06
    ãn
    0.06
     Maur
    0.06
    eer
    0.06
    ì²Ļ
    0.06
    åĨ°åĨ»
    0.06
    Activations Density 0.846%

    No Known Activations