© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 37693
    Prev
    Next
    INDEX
    Explanations

    null or undefined checks

    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
    Ø©
    -0.13
    hood
    -0.10
    psilon
    -0.09
    eer
    -0.09
    ä¸īåı£
    -0.09
    een
    -0.09
    enne
    -0.09
    é¹ıé£ŀ
    -0.08
    人ä¼ļ
    -0.08
    人æĿ¥è¯´
    -0.08
    POSITIVE LOGITS
    ter
    0.09
    ions
    0.09
    ional
    0.09
    缸è¾ħ缸æĪIJ
    0.09
    is
    0.08
    åĴĮ
    0.08
    а
    0.08
    æĬĺä¸įæī£
    0.08
    对
    0.08
    tered
    0.08
    Activations Density 0.005%

    No Known Activations