© 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
    2. Qwen3.5-9B Base
    3. 15-QWENSCOPE-RES-64K
    4. 50001
    Prev
    Next
    INDEX
    Explanations

    sports teams

    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
    ä¸İ被
    -0.08
    å·¥ä½ľä¸İ
    -0.07
    åħ¬åı¸ä¸İ
    -0.07
    è·¯ä¸İ
    -0.07
    缸éļı
    -0.06
    å®ĥä¸İ
    -0.06
    ä¸İåIJĦ
    -0.06
    对被
    -0.06
    åħ¶å®ŀåľ¨
    -0.06
    èīºæľ¯ä¸İ
    -0.06
    POSITIVE LOGITS
    æ¯Ķèĩªå·±
    0.10
     counterparts
    0.08
    åIJĮ为
    0.08
    æĪIJæĮĩ
    0.08
    åIJĮè¡ĮçļĦ
    0.08
    åIJĮè¡Į
    0.08
    iston
    0.08
    çŃīåħ¶ä»ĸ
    0.08
     sesama
    0.08
     collega
    0.07
    Activations Density 0.373%

    No Known Activations