© 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. 21775
    Prev
    Next
    INDEX
    Explanations

    Created by

    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
    ÙĪÙĦÙĬÙĨ
    -0.08
    rimi
    -0.08
    íĥĿ
    -0.08
    çŁ³æ¦´
    -0.08
     Appeal
    -0.08
    æ»Ķæ»Ķ
    -0.07
    ples
    -0.07
    ieti
    -0.07
    åıĪå¤ļ
    -0.07
    íĨ¨
    -0.07
    POSITIVE LOGITS
    __/
    0.07
     module
    0.06
    ç«ĭåĬŁ
    0.06
    ä¸ļ主
    0.06
    رÙĪت
    0.06
     meng
    0.06
     Meh
    0.06
     NotImplemented
    0.06
    heiz
    0.06
    é¡¹çĽ®åIJį称
    0.06
    Activations Density 0.371%

    No Known Activations