© 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. 20243
    Prev
    Next
    INDEX
    Explanations

    domains of work and art

    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
    leck
    -0.08
    ligen
    -0.07
    izzi
    -0.07
    iglia
    -0.07
     Rö
    -0.07
    ç¿°
    -0.07
     forfait
    -0.07
    Õ¸Õ¾
    -0.07
    äºĮ段
    -0.07
    oft
    -0.07
    POSITIVE LOGITS
    追æ±ĤçļĦ
    0.09
    åı²ä¸ĬçļĦ
    0.08
    çļĦæľ¬è´¨
    0.08
    ä¸į该
    0.08
     should
    0.08
    追æ±Ĥ
    0.08
    ä¸İ社ä¼ļ
    0.08
    伦çIJĨ
    0.08
    æĪĸæľįåĬ¡
    0.07
    еÑģÑĤ
    0.07
    Activations Density 0.148%

    No Known Activations