© 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. 60995
    Prev
    Next
    INDEX
    Explanations

    not

    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
    èĢĮä¸įæĺ¯
    -0.12
    èĢĮéĿŀ
    -0.10
    èĢĮä¸į
    -0.09
    èĢĮ没æľī
    -0.09
    å·¥ä½ľçļĦåIJĮæŶ
    -0.08
     whereas
    -0.08
    èĢĮæľª
    -0.08
     statt
    -0.08
    èĢĮä¸įèĥ½
    -0.07
     chứ
    -0.07
    POSITIVE LOGITS
    æĽ´ä¸įæĺ¯
    0.11
     nor
    0.11
    nor
    0.09
     apalagi
    0.08
    æĽ´ä¸įèĥ½
    0.08
     anymore
    0.08
    èĢĮæĺ¯
    0.08
     sekalipun
    0.08
    åIJİèĢħ
    0.08
    æĽ´æ²¡æľī
    0.08
    Activations Density 0.054%

    No Known Activations