© 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. 9029
    Prev
    Next
    INDEX
    Explanations

    math notation and equations

    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
    åĪĻ该
    -0.08
    ingin
    -0.08
    æn
    -0.07
    ÙĩØ©
    -0.07
    /random
    -0.07
    inga
    -0.07
    inie
    -0.07
     finalidade
    -0.07
    <article
    -0.07
    æĩ
    -0.07
    POSITIVE LOGITS
     straightforward
    0.08
     firstly
    0.08
    æ¶Ī
    0.07
    åĴĮç²¾ç¥ŀ
    0.07
    æ¯Ķè¾ĥç®Ģåįķ
    0.07
    åĪĿæŃ¥
    0.07
    åIJĦè¡Į
    0.07
    ç²¾ç¥ŀåĴĮ
    0.06
     noticing
    0.06
    è¡Įèĩ³
    0.06
    Activations Density 0.003%

    No Known Activations