© 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. 48272
    Prev
    Next
    INDEX
    Explanations

    list items or punctuation

    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
    ä»»ä½ķ责任
    -0.09
    çŁ¥ä¹ĭ
    -0.08
    åı£åĮº
    -0.08
    ãģªãģĬ
    -0.08
    åĬªåĬĽåģļåĪ°
    -0.07
    ιά
    -0.07
    æµģè¿ŀ
    -0.07
    adelphia
    -0.07
    åıijå¸ĸ
    -0.07
    ==="
    -0.07
    POSITIVE LOGITS
    åIJĹ
    0.12
    ____
    0.12
     ____
    0.11
     ______
    0.11
    ä»Ģä¹ĪæĦıæĢĿ
    0.11
    ________
    0.10
    _____
    0.10
     _____
    0.10
     __
    0.10
    æĺ¯ä»Ģä¹ĪæĦıæĢĿ
    0.10
    Activations Density 0.110%

    No Known Activations