© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 10634
    Prev
    Next
    INDEX
    Explanations

    invention

    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
    æł¼å°Ķ
    -0.08
    ç¥ĿæĤ¨
    -0.08
    æ£ĢæŁ¥ç»ĵæŀľ
    -0.08
    entin
    -0.08
     xx
    -0.08
    rac
    -0.08
    abal
    -0.08
     perspectiv
    -0.07
    ÑģлÑĥ
    -0.07
    à¤łà¥Ģ
    -0.07
    POSITIVE LOGITS
     âĢ
    0.08
    -
    0.06
    sume
    0.06
    åĨķ
    0.06
    ↵
    0.06
    ault
    0.06
    anko
    0.06
    æ»¡çľ¼
    0.06
    ett
    0.06
      ↵
    0.06
    Activations Density 0.179%

    No Known Activations