© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 25068
    Prev
    Next
    INDEX
    Explanations

    asking "why" or "how"

    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
    åĬ¡
    -0.07
    åĭĻ
    -0.07
    ingang
    -0.07
    éĿ¢å¯¹çĿĢ
    -0.07
    ä¸Ģè¨Ģ
    -0.06
    ragt
    -0.06
    éļ¾çľĭ
    -0.06
    å¾Ĵ
    -0.06
    è°ģ说
    -0.06
    å¸Ĥä¸Ń级人æ°ijæ³ķéĻ¢
    -0.06
    POSITIVE LOGITS
    umba
    0.08
    彦
    0.08
    usta
    0.08
    estar
    0.08
    arez
    0.07
    ä¸įæĺİçļĦ
    0.07
    apiro
    0.07
    åİŁæĸĩ
    0.07
    对åįİ
    0.07
    _pref
    0.07
    Activations Density 0.098%

    No Known Activations