© 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. 10977
    Prev
    Next
    INDEX
    Explanations

    middle OR in

    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
    à¸ģาร
    -0.09
    ä¸Ģ
    -0.09
    zehn
    -0.08
    ä¸Ģ个
    -0.08
    ë¡ľ
    -0.08
    eled
    -0.08
    éĺ¿æĭī伯
    -0.08
    less
    -0.08
    äºĨ
    -0.07
    åĬłæĭ¿å¤§
    -0.07
    POSITIVE LOGITS
    æŁIJç§įç¨ĭ度ä¸Ĭ
    0.11
    åľ°çļĦ
    0.10
    åĮ»çĶŁæĮĩ导ä¸ĭ
    0.10
    æĦıçļĦ
    0.10
    åĮ»çĶŁçļĦæĮĩ导ä¸ĭ
    0.10
    wards
    0.10
    sofar
    0.10
    æŁIJç§įæĦıä¹īä¸Ĭ
    0.09
    sembles
    0.09
     nutshell
    0.09
    Activations Density 0.001%

    No Known Activations