© 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. 46245
    Prev
    Next
    INDEX
    Explanations

    groups of people

    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
    èĽĽ
    -0.07
    åĴĮå¿«ä¹IJ
    -0.07
    ç¥Ŀ大家
    -0.06
    ÙĨاÙĩ
    -0.06
     Rouge
    -0.06
    gnore
    -0.06
    à¸Ľà¸ģ
    -0.06
    eter
    -0.06
    è®©æĽ´å¤ļçļĦ人
    -0.06
    ä¸į顺
    -0.06
    POSITIVE LOGITS
    åĴĮæĪijä¸Ģèµ·
    0.09
     conmigo
    0.08
    éĹ®æĪij
    0.08
    被æĪij
    0.08
    åĴĮæĪij
    0.08
    æīĢåľ¨åľ°åĮº
    0.07
    é¡»çŁ¥
    0.07
    æĹ¢
    0.07
    被åijĬçŁ¥
    0.07
     Berl
    0.07
    Activations Density 0.096%

    No Known Activations