© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 64150
    Prev
    Next
    INDEX
    Explanations

    or or

    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
     instead
    -0.07
     Instead
    -0.07
     invece
    -0.07
     Bu
    -0.07
    æľĹ
    -0.07
    æĪĸèĢħ说
    -0.07
    èºį
    -0.07
    icka
    -0.07
    bu
    -0.06
    undefined
    -0.06
    POSITIVE LOGITS
     alike
    0.10
    à¸ģà¹ĩà¸ķาม
    0.09
    ä¹ŁåĮħæĭ¬
    0.09
    åħ¶ä¸Ģ
    0.08
    ä¹Łç½¢
    0.08
    ä¸įåłª
    0.08
    ä¹Łå¥½
    0.08
     maupun
    0.08
    åľ¨åĨħ
    0.08
    ãĤįãģĨ
    0.07
    Activations Density 0.552%

    No Known Activations