© 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. 28530
    Prev
    Next
    INDEX
    Explanations

    numbers and Christmas

    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
     pur
    -0.08
    åľ¨è¿Ļç§įæĥħåĨµä¸ĭ
    -0.07
     |âĢ¢
    -0.07
    çѱ
    -0.07
    éĩįçĶ³
    -0.07
    ุà¹Īà¸ĩ
    -0.07
    æĭĤ
    -0.06
     вдÑĢÑĥг
    -0.06
     Sur
    -0.06
    æĹ¶è®¸
    -0.06
    POSITIVE LOGITS
    åĭ¤
    0.07
    讨
    0.07
    zis
    0.07
    ascar
    0.07
     sequ
    0.07
    ÙĦÙĬÙĩ
    0.06
    InView
    0.06
    sequ
    0.06
    稽
    0.06
    ä¸įå®ĮçļĦ
    0.06
    Activations Density 0.004%

    No Known Activations