© 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. 32263
    Prev
    Next
    INDEX
    Explanations

    activation by "is" or "in" or "into"

    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
    åģļåĩºæĿ¥çļĦ
    -0.08
     pétr
    -0.08
    大ä¸ĸçķĮ
    -0.07
    enhagen
    -0.07
     mies
    -0.07
    _between
    -0.07
    -between
    -0.07
    aptop
    -0.07
    严éĩįç¨ĭ度
    -0.07
    arkan
    -0.07
    POSITIVE LOGITS
    amat
    0.07
    GUN
    0.06
    HT
    0.06
    CMD
    0.06
    å¾·éŁ³
    0.06
    é¹Ĭ
    0.06
    åİĨæŶ
    0.06
     Lai
    0.06
     Cre
    0.06
    UME
    0.06
    Activations Density 0.002%

    No Known Activations