© 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. 49140
    Prev
    Next
    INDEX
    Explanations

    color definition or plotting

    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
    ews
    -0.06
    enko
    -0.06
    ORY
    -0.06
    æĹłæĦı
    -0.06
    忽
    -0.06
    terms
    -0.06
     {}",
    -0.06
    esh
    -0.06
     intended
    -0.06
    ovsky
    -0.06
    POSITIVE LOGITS
    ķĮ
    0.08
     Suites
    0.08
    WithType
    0.08
    ikä
    0.08
      ↵    ↵
    0.08
    åĨħå¤ĸ
    0.07
    ä¸įå®ĮçļĦ
    0.07
    -kit
    0.07
    夷
    0.07
    loys
    0.07
    Activations Density 0.116%

    No Known Activations