© 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. 56988
    Prev
    Next
    INDEX
    Explanations

    integrated circuits

    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
    ç¡®
    -0.07
    æİĮæı¡
    -0.06
    íĻĶëIJľ
    -0.06
    «
    -0.06
    ERE
    -0.06
     «
    -0.06
    ãĤī
    -0.05
    OVO
    -0.05
    AGMA
    -0.05
    пенÑĮ
    -0.05
    POSITIVE LOGITS
    两ä¸į误
    0.09
    å¹´çļĦæŶåĢĻ
    0.07
    åħļé£İ
    0.07
    æĹ¥æ¸¸
    0.07
    ignment
    0.07
    山头
    0.07
    olÃŃ
    0.07
    éķ¿çĽ¸
    0.07
    ิà¹Īà¸Ļ
    0.07
    #undef
    0.06
    Activations Density 0.336%

    No Known Activations