© 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. 44762
    Prev
    Next
    INDEX
    Explanations

    stream or line processing

    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
    Negative Logits
    mena
    -0.09
    æ°ijäºĭè¡Į为
    -0.07
    à¸Īา
    -0.07
     automatica
    -0.07
    æıĴä¸Ĭ
    -0.07
     departing
    -0.07
     Assigned
    -0.07
    bey
    -0.07
     Automatic
    -0.07
    icia
    -0.07
    POSITIVE LOGITS
     instead
    0.08
    cif
    0.07
    ç´§åĩij
    0.07
     dynamically
    0.07
    åıªæĺ¾ç¤º
    0.07
     live
    0.07
    instead
    0.07
    ä»£æĽ¿
    0.07
     memory
    0.07
     Instead
    0.07
    Activations Density 0.064%

    No Known Activations