© 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. 38438
    Prev
    Next
    INDEX
    Explanations

    contiguous

    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
    atoire
    -0.10
    awang
    -0.08
    itzen
    -0.08
    kund
    -0.08
    stands
    -0.08
     Fires
    -0.08
    .TYPE
    -0.08
     Condiciones
    -0.08
    anty
    -0.08
    ulte
    -0.08
    POSITIVE LOGITS
     contiguous
    0.10
    æľĢéķ¿çļĦ
    0.08
    è¿ŀç»ŃçļĦ
    0.08
     uninterrupted
    0.08
    éĽĨä¸ŃçļĦ
    0.08
    符
    0.07
    ä¸Ķ
    0.07
     blocks
    0.07
     span
    0.07
    åŃIJ
    0.07
    Activations Density 0.008%

    No Known Activations