© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 46581
    Prev
    Next
    INDEX
    Explanations

    since, because, as

    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
    è¿Ļå°±æĺ¯æĪij
    -0.08
    å¿«æĿ¥
    -0.08
    arı
    -0.07
    inned
    -0.07
     dennoch
    -0.07
    .ac
    -0.07
    èĻı
    -0.07
    åı¯æĥľäºĨ
    -0.07
    æĪijåį´
    -0.07
    è§ģæѤ
    -0.07
    POSITIVE LOGITS
     ordinarily
    0.09
    éĢļå¸¸åľ¨
    0.08
     Normally
    0.08
    since
    0.08
    çݰ代社ä¼ļ
    0.08
    æĪijä»¬çŁ¥éģĵ
    0.08
    éĢļ常æĥħåĨµä¸ĭ
    0.08
    ileo
    0.08
    æĪij们éĥ½çŁ¥éģĵ
    0.08
    ä¸ĢèĪ¬èĢĮè¨Ģ
    0.08
    Activations Density 0.687%

    No Known Activations