© 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. 40978
    Prev
    Next
    INDEX
    Explanations

    code tokens: vector, map, list

    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
    reira
    -0.09
    笹
    -0.09
    оÑĤоÑĢ
    -0.08
    åĪĽæĸ°ç²¾ç¥ŀ
    -0.07
    ieu
    -0.07
    æ´ĹéĿ¢
    -0.07
    éħĿ
    -0.07
    sse
    -0.07
    注åĨĮèµĦæľ¬ä¸º
    -0.07
    ãĤīãģĦ
    -0.07
    POSITIVE LOGITS
    zinho
    0.07
    çĦī
    0.06
    اصÙĦ
    0.06
    éķ¿è¾¾
    0.06
    oldt
    0.06
    æŀľçĦ¶
    0.06
    .Builder
    0.06
    ÑĤай
    0.06
    Ñĩик
    0.06
    воло
    0.06
    Activations Density 0.022%

    No Known Activations