© 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. 21343
    Prev
    Next
    INDEX
    Explanations

    us or our

    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
     himself
    -0.10
     oneself
    -0.09
    ä»ĸèĩªå·±çļĦ
    -0.09
     ponerse
    -0.09
     ÙĨÙģسÙĩ
    -0.09
     egli
    -0.08
     conmigo
    -0.08
     ÙĦÙĨÙģس
    -0.08
     farsi
    -0.08
    çĶ¸
    -0.08
    POSITIVE LOGITS
     team
    0.08
     ourselves
    0.08
    ç»Ļä½łä»¬
    0.08
     ваÑģ
    0.08
     ÙĨØŃÙĨ
    0.07
    ethod
    0.07
    为æĤ¨æıIJä¾Ľ
    0.07
    æ¯Ķä½ł
    0.07
     ÙĦÙĥÙħ
    0.07
    åĽ¢éĺŁ
    0.07
    Activations Density 0.966%

    No Known Activations