© 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. 23988
    Prev
    Next
    INDEX
    Explanations

    Law & Order, Duty, episode, Premium

    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
    æ»Ķæ»Ķ
    -0.08
    inato
    -0.08
    Õ½
    -0.07
    bef
    -0.07
     Bela
    -0.07
    ante
    -0.07
    ingat
    -0.07
    .setter
    -0.07
    icode
    -0.07
    ainer
    -0.07
    POSITIVE LOGITS
    ãĢĭ
    0.08
    æĺ¯ä¸Ģéĥ¨
    0.07
    ®
    0.07
     пеÑĢеб
    0.07
    导读
    0.07
    æīĢè½½
    0.07
    åİŁçīĪ
    0.06
    ä¸Ģ书
    0.06
    -esque
    0.06
    åºĶæĢ¥ç®¡çIJĨ
    0.06
    Activations Density 0.008%

    No Known Activations