© 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. 24461
    Prev
    Next
    INDEX
    Explanations

    loop and for loops

    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
    дÑĮми
    -0.09
    æĩ¿
    -0.08
    è¿Ļæł·ä¸Ģç§į
    -0.08
    ìĶ©
    -0.08
    egah
    -0.08
    åIJĪ家
    -0.08
    okane
    -0.08
     Mestre
    -0.08
     polled
    -0.08
    çĨŁçļĦ
    -0.08
    POSITIVE LOGITS
    ç»ĵæĿŁåIJİ
    0.07
    ä¸ŃçļĦ
    0.07
    èĪįå¾Ĺ
    0.06
    头
    0.06
     aimed
    0.06
    ä¸ŃçļĦæķ°æį®
    0.06
    èĩ³
    0.06
     routine
    0.06
    åĨħçļĦ
    0.06
    éĩĮçļĦ
    0.06
    Activations Density 0.006%

    No Known Activations