© 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. 28405
    Prev
    Next
    INDEX
    Explanations

    NSIndexPath call signature

    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
    rement
    -0.08
    reiro
    -0.08
    æ¡¥éķĩ
    -0.08
     اÙĦÙģعÙĦ
    -0.08
    µľ
    -0.08
    astas
    -0.07
    å¿ĥä¸Ńæľīæķ°
    -0.07
    нÑĥÑģ
    -0.07
    acco
    -0.07
    reis
    -0.07
    POSITIVE LOGITS
    orz
    0.08
    ç»ļ
    0.07
    æĪĸ缴æİ¥
    0.06
    çѱ
    0.06
    ç¿İ
    0.06
    (
    0.06
    æľīåħ³äºİ
    0.06
    (optional
    0.06
    /Resources
    0.06
    æĪĸèĢħ缴æİ¥
    0.05
    Activations Density 0.094%

    No Known Activations