© 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. 21050
    Prev
    Next
    INDEX
    Explanations

    compared to lesser

    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
     propor
    -0.08
     proportional
    -0.08
    çļĦæ¯Ķä¾ĭ
    -0.08
    xd
    -0.07
    gid
    -0.07
    æĺ¾èijĹæıIJé«ĺ
    -0.07
    æ¯Ķä¾ĭ为
    -0.07
    éģ¿
    -0.07
    æ¯Ķä¾ĭ
    -0.07
    aired
    -0.07
    POSITIVE LOGITS
    åıªä¼ļ
    0.07
     fewer
    0.07
    èľľ
    0.07
     اÙĦÙħزÙĬد
    0.07
     compared
    0.07
    æ¦Ľ
    0.07
    ä¼ģä¸ļä¸ļåĬ¡
    0.07
    isan
    0.07
    éļ¾å¾Ĺ
    0.07
    SES
    0.06
    Activations Density 0.007%

    No Known Activations