© 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. 47141
    Prev
    Next
    INDEX
    Explanations

    cell objects

    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
    æī
    -0.07
     chừng
    -0.06
    è°Ī
    -0.06
    å¿ĹæĪIJ
    -0.06
    iba
    -0.06
    æľªè§ģ
    -0.06
    æĺ¯ä¸Ģ个å¾Ī
    -0.06
    å
    -0.06
    à·Ķà·Ģ
    -0.06
    åĴı
    -0.06
    POSITIVE LOGITS
    à¸Ķà¹īวยà¸ģัà¸Ļ
    0.08
    å°½ãģı
    0.08
    æ´»åĬ¨ç»ĵæĿŁåIJİ
    0.08
    åĴĮéĿŀ
    0.08
    -only
    0.07
    -exclusive
    0.07
    为主导
    0.07
    -dominated
    0.07
    emberg
    0.07
     outnumber
    0.07
    Activations Density 0.005%

    No Known Activations