© 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. 49597
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     Uniti
    -0.08
    :host
    -0.07
    à§įষ
    -0.07
    idio
    -0.07
    panion
    -0.07
    داÙħ
    -0.07
    åħ¶ä¸İ
    -0.07
    åı¯å®ŀçİ°
    -0.07
    迹
    -0.07
    illion
    -0.07
    POSITIVE LOGITS
    åıĸå¾Ĺ
    0.07
    æ··
    0.07
    mares
    0.06
    _try
    0.06
    å¾ĹåĪ°
    0.06
    éĴĪ对
    0.06
    ħ
    0.06
    让人æĦŁåĪ°
    0.06
     silent
    0.06
    潺
    0.06
    Activations Density 0.000%

    No Known Activations