© 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. 29236
    Prev
    Next
    INDEX
    Explanations

    first, ground, lowest, leading, fundamental

    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
    éĶŃ
    -0.07
    endt
    -0.07
    ä¸į太好
    -0.07
    pers
    -0.07
     Harden
    -0.07
    åIJĮçŃī
    -0.07
    _endian
    -0.07
    okens
    -0.07
    æ³¾
    -0.07
    pdo
    -0.07
    POSITIVE LOGITS
    åĴĮæľĢ
    0.12
    ä¹Łæĺ¯æľĢ
    0.12
    åĴĮ第äºĮ
    0.11
    æĺ¯ç¬¬ä¸Ģ
    0.10
    argest
    0.10
    æĺ¯æľĢ
    0.09
    æľĢ为
    0.09
     ê°Ģìŀ¥
    0.09
    allest
    0.09
    (first
    0.09
    Activations Density 0.033%

    No Known Activations