© 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. 13661
    Prev
    Next
    INDEX
    Explanations

    certain selections

    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
    åĵģçīĮ形象
    -0.08
    ADED
    -0.07
    åĵģçīĮæݨ广
    -0.07
    åį°åıij
    -0.07
    loaded
    -0.07
    æ´¾åıij
    -0.07
    Discover
    -0.07
     Discover
    -0.07
    Loaded
    -0.07
    omot
    -0.07
    POSITIVE LOGITS
    åıĸèĩª
    0.10
    éĢīåıĸ
    0.08
    éĩįæĸ°
    0.08
    æĿ¥èĩª
    0.08
     new
    0.08
     selectively
    0.08
    æĭ¼æİ¥
    0.08
    æĿ¥èĩªäºİ
    0.08
     nueva
    0.08
     concaten
    0.08
    Activations Density 0.143%

    No Known Activations