© 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. 46028
    Prev
    Next
    INDEX
    Explanations

    many times

    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
    ibal
    -0.08
    поло
    -0.07
    å±Ĭ
    -0.07
    Õ¹
    -0.07
     Welfare
    -0.07
    æĪª
    -0.07
    Encoder
    -0.07
    第åħŃ
    -0.06
    å¥ĩ迹
    -0.06
    ìľĦë¡ľ
    -0.06
    POSITIVE LOGITS
    ãģļãĤĮ
    0.07
    quent
    0.07
    맥
    0.06
    æį·
    0.06
     overhead
    0.06
    å¾·åįİ
    0.06
     submissions
    0.06
    صات
    0.06
    oday
    0.06
    زاÙħ
    0.06
    Activations Density 0.013%

    No Known Activations