© 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. 51431
    Prev
    Next
    INDEX
    Explanations

    sample data files and inserts

    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
    .combine
    -0.08
    oggi
    -0.07
    nameof
    -0.07
     táºŃn
    -0.07
    /compiler
    -0.07
    åĪĨå¤ĸ
    -0.07
    ÎŃÏģ
    -0.07
    åŁ¹æł¹
    -0.07
    extended
    -0.06
    èĥ½ä¿ĥè¿Ľ
    -0.06
    POSITIVE LOGITS
     hardcoded
    0.08
    ä»¿çľŁ
    0.08
     realistically
    0.08
     Fiction
    0.08
     simulated
    0.08
     fictional
    0.08
     Stub
    0.07
    å¿ĥè¡Ģ
    0.07
    åı¯ä¾Ľ
    0.07
     sud
    0.07
    Activations Density 0.059%

    No Known Activations