© 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. 15124
    Prev
    Next
    INDEX
    Explanations

    induction

    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
    appings
    -0.07
    amiento
    -0.07
    ights
    -0.07
    amp
    -0.07
    ican
    -0.07
    imea
    -0.07
    è¿ĻäºĽä¿¡æģ¯
    -0.07
    িà¦ķà§įষ
    -0.07
    quiv
    -0.07
    prite
    -0.07
    POSITIVE LOGITS
     azon
    0.06
    -held
    0.06
     onData
    0.06
    à¸ģรà¸ĵà¹Į
    0.06
    oras
    0.06
    æ³ķ
    0.06
    اث
    0.06
    verified
    0.06
    éĥ¡
    0.06
    Verified
    0.06
    Activations Density 0.002%

    No Known Activations