© 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. 42660
    Prev
    Next
    INDEX
    Explanations

    or contrast

    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
    å¢ĥçļĦ
    -0.07
     Proper
    -0.07
    ä¸ĸçķĮä¸Ĭ
    -0.06
    å¢ĥ
    -0.06
    æľīåħ³çļĦ
    -0.06
    ä¸įåħ¨
    -0.06
     proper
    -0.06
    izz
    -0.06
    缸åħ³çļĦ
    -0.06
    åIJĮ
    -0.06
    POSITIVE LOGITS
     vs
    0.14
    çŃīä¸įåIJĮ
    0.13
     versus
    0.11
    æĬijæĪĸ
    0.11
    ä¸įåIJĮç±»åŀĭçļĦ
    0.10
    ä¸įåIJĮç±»åŀĭ
    0.10
    亦æĪĸæĺ¯
    0.10
    vs
    0.09
    ç±»çŃī
    0.09
    æľīä¸įåIJĮçļĦ
    0.09
    Activations Density 0.074%

    No Known Activations