© 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. 23254
    Prev
    Next
    INDEX
    Explanations

    teeth care or CPU

    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
    çļĦæŶåĢĻäºĨ
    -0.08
    éĥ½æĺ¯åĽłä¸º
    -0.08
    æľĢæľĢ
    -0.08
    åŃIJäºĨ
    -0.08
    omen
    -0.08
    éĥ½åĥı
    -0.08
    å·²ç»ıè¿ĩåİ»
    -0.08
    æĺ¯ä¸įå¤Ł
    -0.08
    æĢ»ä½ĵèĢĮè¨Ģ
    -0.07
    æĪijæĺİçĻ½äºĨ
    -0.07
    POSITIVE LOGITS
    ä¹Łä¸įä¾ĭå¤ĸ
    0.14
     thereof
    0.13
    à¸Īึà¸ĩ
    0.12
     thereafter
    0.12
     therein
    0.12
    åĽłèĢĮ
    0.11
     consequently
    0.11
     therefore
    0.11
    åĪĻ
    0.11
     accordingly
    0.11
    Activations Density 0.023%

    No Known Activations