© 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. 48265
    Prev
    Next
    INDEX
    Explanations

    logic, database keys, sponsorship, creation date, decisions, symbols, random digits

    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
    unyi
    -0.09
    niest
    -0.08
    ÙĦد
    -0.08
    ZION
    -0.08
    ongyang
    -0.08
     ric
    -0.08
    ojis
    -0.07
    ATORI
    -0.07
    åĪĨå¸ĥå¦Ĥä¸ĭ
    -0.07
    Ult
    -0.07
    POSITIVE LOGITS
    æĹłæĥħçļĦ
    0.07
    åIJĮä¸Ĭ
    0.06
    iteral
    0.06
    izard
    0.06
    åĩºèĩª
    0.06
    åIJĮä¸Ģ
    0.06
    常è¯Ĩ
    0.06
    usser
    0.06
    太
    0.06
    uvan
    0.06
    Activations Density 0.003%

    No Known Activations