© 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. 56833
    Prev
    Next
    INDEX
    Explanations

    quality

    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
    abas
    -0.08
     ìŀijìļ©
    -0.07
     Ùħشت
    -0.07
    å¢ŀæķĪ
    -0.07
    EGI
    -0.07
    åIJijèį£
    -0.07
    åįĥåįĥ
    -0.07
     sendData
    -0.07
    iggio
    -0.07
    æĸ¹ä¾¿çļĦ
    -0.07
    POSITIVE LOGITS
     quality
    0.11
    æĪIJåĵģ
    0.10
     resulting
    0.10
     desired
    0.10
    quality
    0.10
    ä»ķä¸ĬãģĮ
    0.10
     íĴĪì§Ī
    0.10
    Quality
    0.10
    è´¨éĩı
    0.09
     desirable
    0.09
    Activations Density 0.375%

    No Known Activations