© 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. 50486
    Prev
    Next
    INDEX
    Explanations

    small group or few

    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
    æľĢå·®
    -0.08
    _MIC
    -0.08
    /npm
    -0.08
    DetailsService
    -0.07
    annen
    -0.07
    à¸Ńà¹Īà¸Ńà¸Ļ
    -0.07
    äºĮä½į
    -0.07
    /kubernetes
    -0.07
    yte
    -0.07
    empa
    -0.07
    POSITIVE LOGITS
    寥寥
    0.12
    æķ°éĩıæľīéĻIJ
    0.12
     few
    0.12
    å±ĪæĮĩ
    0.11
    å°ijæķ°
    0.11
     fewer
    0.11
    ç¨Ģ缺
    0.11
    few
    0.11
     Few
    0.11
    æŀģå°ijæķ°
    0.11
    Activations Density 0.261%

    No Known Activations