© 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. 51271
    Prev
    Next
    INDEX
    Explanations

    non-english characters

    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
    pone
    -0.09
    angkat
    -0.07
    bedingt
    -0.07
     ngầm
    -0.07
    igel
    -0.07
    çļĦ鼨
    -0.07
    alisasi
    -0.06
     gác
    -0.06
    å¤§éĽ¨
    -0.06
    ç«ĭ交
    -0.06
    POSITIVE LOGITS
     Ñģебе
    0.08
    åı¯ä»¥åIJĹ
    0.08
     Schle
    0.07
    اء
    0.07
    using
    0.07
     using
    0.06
    hop
    0.06
    заÑĢ
    0.06
    èĢ¶
    0.06
     иÑģполÑĮзÑĥÑı
    0.06
    Activations Density 0.269%

    No Known Activations