© 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. 2516
    Prev
    Next
    INDEX
    Explanations

    groups of numbers

    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
    åIJİèĢħ
    -0.08
     latter
    -0.08
    åį³ä¾¿å¦ĤæѤ
    -0.08
    ä¸İä¹ĭ
    -0.07
     thereof
    -0.07
    ä¹Łæĺ¯å¦ĤæѤ
    -0.07
    åı¦å¤ĸä¸Ģç§į
    -0.07
    ':''
    -0.07
    ê·¸ëŁ¬
    -0.07
    åı¦ä¸Ģæĸ¹
    -0.07
    POSITIVE LOGITS
     infatti
    0.10
     ugyanis
    0.08
     bowiem
    0.08
     totiž
    0.08
    !");
    0.08
    ä½Ĩä¸įéĻIJäºİ
    0.07
    ãĢįãĢģãĢĮ
    0.07
    ”;
    0.07
    ardin
    0.07
    ãĢįãĢĮ
    0.07
    Activations Density 0.286%

    No Known Activations