© 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. 19297
    Prev
    Next
    INDEX
    Explanations

    I want

    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
    åĪ¹éĤ£
    -0.07
    ulp
    -0.07
    æĹłè®ºæĺ¯åľ¨
    -0.07
    ä»»ä½ķåħ¶ä»ĸ
    -0.07
    çĽ¸å¯¹çļĦ
    -0.07
    ä¸įä¼ļåĨį
    -0.07
    ger
    -0.06
    æĸ°æĺŁ
    -0.06
    .enabled
    -0.06
    ovan
    -0.06
    POSITIVE LOGITS
    éĿ¢å¹¿
    0.08
    ä¹Łåı¯ä»¥ä½¿çĶ¨
    0.08
     Ñģлож
    0.07
    åĽ½ç«ĭ
    0.07
    没å¿ħè¦ģ
    0.07
    å·²ç»ıå¾Ī
    0.07
    abad
    0.07
    æķŀ
    0.07
    ç½Ĺå¾·
    0.07
    æĪijä¸įæĥ³
    0.07
    Activations Density 0.097%

    No Known Activations