© 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. 57091
    Prev
    Next
    INDEX
    Explanations

    ASF, nurses, breast cancer

    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
    خت
    -0.07
    athed
    -0.07
    bower
    -0.07
    次年
    -0.07
    çİ©
    -0.07
    اة
    -0.07
    _DEFINE
    -0.07
    gree
    -0.07
     degrees
    -0.07
    degrees
    -0.06
    POSITIVE LOGITS
    ä¸İåħ¶ä»ĸ
    0.15
    èĪĩåħ¶ä»ĸ
    0.12
    对åħ¶ä»ĸ
    0.12
    ä¸İåħ¶å®ĥ
    0.11
    æľ¬èº«çļĦ
    0.10
    缴æİ¥æĪĸ
    0.10
    åĪ°åħ¶ä»ĸ
    0.10
     alone
    0.09
     itself
    0.09
    åĴĮåħ¶ä»ĸ
    0.09
    Activations Density 0.288%

    No Known Activations