© 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. 16532
    Prev
    Next
    INDEX
    Explanations

    JSON keys and values

    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
    baugh
    -0.09
    /../
    -0.07
    ulla
    -0.07
    urt
    -0.07
    /null
    -0.07
    /manage
    -0.07
    inaldo
    -0.07
    西å®ģ
    -0.07
    aine
    -0.06
    士æŀĹ
    -0.06
    POSITIVE LOGITS
    _callbacks
    0.07
    _refer
    0.07
     ):
    0.07
    å²ĽçļĦ
    0.07
    _serial
    0.07
    endar
    0.07
    é¾ĻçļĦ
    0.07
    ãģĿãģ®ä»ĸãģ®
    0.07
    æī©å±ķèµĦæĸĻ
    0.07
    ãģĿãĤĮãģĮ
    0.07
    Activations Density 0.051%

    No Known Activations