© 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. 42899
    Prev
    Next
    INDEX
    Explanations

    place names

    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
    åħ¶éģĵ
    -0.07
    WithType
    -0.07
    .Loader
    -0.07
    ãģłãģĭãĤīãģĵãģĿ
    -0.07
    ç§įåħ»
    -0.07
    æīĢä»¥ä½ł
    -0.07
    å¾Ĺ天çĭ¬
    -0.06
    æľīçĶŁ
    -0.06
    ChangedEventArgs
    -0.06
    ĥĿ
    -0.06
    POSITIVE LOGITS
    姥
    0.08
    ä¸Ģæł·çļĦ
    0.07
     (?)
    0.07
    (?)
    0.07
    絡
    0.07
     (!
    0.07
    大å°ıçļĦ
    0.07
    ish
    0.07
    ä¸ĢèĪ¬çļĦ
    0.06
    -like
    0.06
    Activations Density 1.223%

    No Known Activations