© 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. 16681
    Prev
    Next
    INDEX
    Explanations

    background radiation

    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
    UPER
    -0.07
    assi
    -0.06
    atsu
    -0.06
    apper
    -0.06
    quo
    -0.06
     owner
    -0.06
    çĻĮ
    -0.06
    .owner
    -0.06
     Inspiration
    -0.06
    èģļ
    -0.06
    POSITIVE LOGITS
    å©´ç«¥
    0.08
    æijĩ篮
    0.08
    à¹Į
    0.08
    glich
    0.08
    Õº
    0.07
     Babies
    0.07
    辩
    0.07
    æľī丰å¯ĮçļĦ
    0.07
    ä¸Ģå²ģ
    0.07
    ãĤ¯ãĥ«
    0.07
    Activations Density 0.005%

    No Known Activations