© 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. 7730
    Prev
    Next
    INDEX
    Explanations

    months duration

    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
    天æĺİ
    -0.08
    ä»ĬæĻļ
    -0.08
    ä»Ĭ天ä¸ĬåįĪ
    -0.08
    ä»Ĭå¤ľ
    -0.08
    åĽ½åįİ
    -0.08
    psilon
    -0.08
    ลม
    -0.08
    coup
    -0.07
    æĺ¨æĻļ
    -0.07
    aciente
    -0.07
    POSITIVE LOGITS
    -long
    0.10
    åįĬå¹´çļĦ
    0.09
    /year
    0.08
    /month
    0.08
     duration
    0.08
     ago
    0.08
    ä¹ĭä¹ħ
    0.08
    -month
    0.08
    æľŁéĹ´çļĦ
    0.08
     months
    0.08
    Activations Density 0.082%

    No Known Activations