© 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. 50504
    Prev
    Next
    INDEX
    Explanations

    of [noun]

    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
    óz
    -0.08
    ÙĪضة
    -0.07
    .sql
    -0.07
     acaso
    -0.07
    uz
    -0.07
     itself
    -0.07
    æŁIJç§įæĦıä¹īä¸Ĭ
    -0.07
    elen
    -0.07
    BOOLE
    -0.06
    uzzi
    -0.06
    POSITIVE LOGITS
     ìĿ´ìľłë¡ľ
    0.08
    æŶéĹ´éĩĮ
    0.08
    æĹ¥åŃIJéĩĮ
    0.07
    ity
    0.07
    åĮªæµħ
    0.07
    ness
    0.07
    èĢĮä½ł
    0.07
    èĢĮä¸Ķæĺ¯
    0.07
    æĥħåĨµä¸ĭ
    0.07
    å¦Ĥèĭ¥
    0.07
    Activations Density 0.436%

    No Known Activations