© 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. 43553
    Prev
    Next
    INDEX
    Explanations

    youtube links and video titles

    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
    åľ¨çº¿éĺħ读
    -0.08
    ä¹Ŀ游
    -0.08
     Pulitzer
    -0.08
    ä¸ĭè½½æĬ¥åijĬ
    -0.07
    fax
    -0.07
    稿件æĿ¥æºIJ
    -0.07
     writable
    -0.07
    Descriptors
    -0.07
    æݨèįIJéĺħ读
    -0.07
    Wins
    -0.07
    POSITIVE LOGITS
    è§Ĩé¢ij
    0.10
     YouTube
    0.10
    .youtube
    0.10
    YouTube
    0.10
     video
    0.10
    è§Ĩé¢ijä¸Ń
    0.09
     videos
    0.09
    ãĥģãĥ£ãĥ³ãĥįãĥ«
    0.09
     видео
    0.08
    youtu
    0.08
    Activations Density 0.274%

    No Known Activations