© 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. 46320
    Prev
    Next
    INDEX
    Explanations

    links, furthermore, but

    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
    ä¹Łåı¯ä»¥æĺ¯
    -0.06
     ero
    -0.06
     sym
    -0.06
    lisi
    -0.06
     Normally
    -0.06
    è¿Ļåı¯æĺ¯
    -0.06
    å¯ĮåIJ«
    -0.06
    \Command
    -0.06
    \Cache
    -0.06
     dico
    -0.06
    POSITIVE LOGITS
    çķ¥æĺ¾
    0.09
     unnecessarily
    0.09
    è¾ĥæĹ©
    0.09
    åĭģ
    0.09
    åıªé¡¾
    0.09
    åIJĮæł·
    0.08
    ç«ŁçĦ¶
    0.08
    æ¯Ķè¾ĥç®Ģåįķ
    0.08
    å¾ĪæĹ©å°±
    0.08
    евиÑĩ
    0.08
    Activations Density 0.009%

    No Known Activations