© 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. 30360
    Prev
    Next
    INDEX
    Explanations

    counting or listing items

    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
    è¸ıè¸ıå®ŀå®ŀ
    -0.07
    æµ·
    -0.06
    æĿĤ
    -0.06
     hab
    -0.06
    C
    -0.06
     supr
    -0.06
    æѦå¨ģ
    -0.06
    iche
    -0.06
    ÐłÐIJÐĴ
    -0.06
    严èĤĥ
    -0.05
    POSITIVE LOGITS
     Schmid
    0.08
    kung
    0.08
    ilter
    0.08
    ä¸Ĭä¸Ģç«ł
    0.08
    à°Łà±į
    0.08
    累计
    0.08
    ÃŃž
    0.08
    edList
    0.08
    Õ¡Öģ
    0.08
    NCY
    0.07
    Activations Density 0.042%

    No Known Activations