© 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. 61625
    Prev
    Next
    INDEX
    Explanations

    completed, dead, months, differentiated, mature, committed

    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
    ä¸Ģ缴
    -0.08
     solange
    -0.08
    ä¸Ģ缴åĪ°
    -0.08
    ä¸Ģ缴åĿļæĮģ
    -0.07
    arger
    -0.07
    çIJ¦
    -0.07
    íķĺëĭ¤ê°Ģ
    -0.07
    æľĢåĪĿãģ¯
    -0.07
    ä¸ĢçĽ´è¢«
    -0.07
    uddle
    -0.07
    POSITIVE LOGITS
    æ¸Īãģ¿
    0.13
    æĪIJçĨŁçļĦ
    0.12
    äºĨçļĦ
    0.12
     already
    0.12
    æĪIJçĨŁ
    0.12
    ä¸įä¼ļåĨį
    0.12
    å·²ç»ıå®Įåħ¨
    0.11
    ä¸įåĨįæľī
    0.11
    ä¹Łå·²ç»ı
    0.11
    ä¸įåĨį
    0.11
    Activations Density 0.148%

    No Known Activations