© 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. 38584
    Prev
    Next
    INDEX
    Explanations

    spatial distribution or relation

    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
    åħ¨éĥ½æĺ¯
    -0.06
    ivor
    -0.06
    åľ¨åİŁ
    -0.06
    .original
    -0.06
    idden
    -0.06
    enze
    -0.06
    atat
    -0.06
    pieces
    -0.06
    ç£
    -0.06
    åİŁæĿ¥æĺ¯
    -0.06
    POSITIVE LOGITS
    横åIJij
    0.08
    ä»°
    0.08
    纵
    0.08
    纵åIJij
    0.08
    ìļ°
    0.08
     geographic
    0.08
    横
    0.08
    ynes
    0.08
     geographical
    0.08
     spatial
    0.08
    Activations Density 0.288%

    No Known Activations