© 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. 48922
    Prev
    Next
    INDEX
    Explanations

    numbers and ordinals

    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
     unif
    -0.08
    ãģ«ãĤĪãģ£ãģ¦ãģ¯
    -0.07
    æ½°
    -0.07
    peen
    -0.07
    ãĥ©ãĥ«
    -0.07
    é®®
    -0.07
    GMT
    -0.07
    äºĮ段
    -0.07
    .unpack
    -0.07
    atel
    -0.07
    POSITIVE LOGITS
     ods
    0.07
    ç¬¬åĽĽæ¬¡
    0.07
    çĶŁæĢģæĸĩæĺİ建设
    0.07
    úl
    0.07
    ä¼ģä¸ļä¿¡æģ¯
    0.07
    æŁ¥æŁ¥
    0.07
    åıĬ以ä¸Ĭ
    0.07
    级
    0.07
    째
    0.06
     ÑģооÑĤвеÑĤÑģÑĤвÑĥ
    0.06
    Activations Density 0.037%

    No Known Activations