© 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. 26614
    Prev
    Next
    INDEX
    Explanations

    key-value pairs

    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
    coni
    -0.08
    å¯¹æľ¬æ¬¡
    -0.08
    erbe
    -0.08
    erio
    -0.07
    é©Ń
    -0.07
    éļĬçļĦ
    -0.07
     обÑĢазов
    -0.07
    IGN
    -0.07
    æĢ»éĥ¨ä½įäºİ
    -0.07
    arium
    -0.07
    POSITIVE LOGITS
    å¾ħ
    0.07
    çĮ
    0.07
    pron
    0.06
    æĽ´æ·±
    0.06
     {}'.
    0.06
    ä¸įåIJĮçļĦ
    0.06
    足
    0.06
    룬ìĬ¤
    0.06
    äten
    0.06
    ç¼Ń
    0.06
    Activations Density 0.058%

    No Known Activations