© 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. 11616
    Prev
    Next
    INDEX
    Explanations

    the

    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
    øj
    -0.07
    ans
    -0.07
    æ¯Ķå¦Ĥ说
    -0.06
    ä¸ĢèĪ¬åľ¨
    -0.06
    ä¸ĢèĪ¬æĿ¥è¯´
    -0.06
    åľ¨åĪ«äºº
    -0.06
     maybe
    -0.06
    æ¯Ķè¾ĥ好çļĦ
    -0.06
     funny
    -0.06
    åĿ¤
    -0.06
    POSITIVE LOGITS
    ZION
    0.08
    缸åħ³æݨèįIJ
    0.07
    æĹ¢è¦ģ
    0.07
    iren
    0.07
    æĮ½
    0.07
     곧
    0.07
    llib
    0.07
    ifest
    0.07
    ired
    0.07
    èĢĮä»Ĭ
    0.07
    Activations Density 0.026%

    No Known Activations