© 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. 25875
    Prev
    Next
    INDEX
    Explanations

    depends on, would get, choice

    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
    éĢļè¿ĩè¿ĻäºĽ
    -0.07
    鬣
    -0.07
    æľīæķĪæŀľ
    -0.06
    æĺ¯éĢļè¿ĩ
    -0.06
    rof
    -0.06
    ä¸Ģä¼ļåĦ¿
    -0.06
    æľĢæĹ©çļĦ
    -0.06
     unlike
    -0.06
    éĢļè¿ĩ
    -0.06
     illeg
    -0.06
    POSITIVE LOGITS
    æĢ§ä»·æ¯Ķ
    0.13
    æĢ§ä»·æ¯Ķé«ĺ
    0.11
    综åIJĪèĢĥèĻij
    0.10
    æī¬éķ¿
    0.10
     recommendation
    0.10
    ä¼ĺåħĪèĢĥèĻij
    0.10
    åıĸèĪį
    0.10
    æĽ´éĢĤåIJĪ
    0.10
    é«ĺæĢ§ä»·æ¯Ķ
    0.10
    ä¹ĭéĢī
    0.10
    Activations Density 0.178%

    No Known Activations