© 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. 3434
    Prev
    Next
    INDEX
    Explanations

    code keywords and punctuation

    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
    à¹Ĥà¸ģ
    -0.06
    رد
    -0.06
     #[
    -0.06
    åľ¨çľī
    -0.06
     #__
    -0.06
    æıĴä¸Ĭ
    -0.06
    ä¸įè¯Ĩ
    -0.06
     Ax
    -0.06
    باب
    -0.06
     Avril
    -0.06
    POSITIVE LOGITS
    .selenium
    0.08
    è·³åĩº
    0.08
    ì¹
    0.08
    å¹³æĺĵè¿ij
    0.08
    åľ°ä¹ħ
    0.08
    {}\
    0.07
    ERVER
    0.07
    _mt
    0.07
    éĿĴ天
    0.07
    tright
    0.07
    Activations Density 0.031%

    No Known Activations