© 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. 1579
    Prev
    Next
    INDEX
    Explanations

    circular or looping operations

    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
    upas
    -0.10
    aturi
    -0.09
    imson
    -0.09
    Ïĥια
    -0.08
    å¾·åŁº
    -0.08
    allet
    -0.08
    anian
    -0.08
    eppe
    -0.08
    人以ä¸ĭ
    -0.08
    fér
    -0.08
    POSITIVE LOGITS
    横
    0.07
    _cc
    0.07
    横跨
    0.07
    温
    0.07
    å¼Ģè£Ĥ
    0.06
    æĴŀ
    0.06
     Gap
    0.06
     continuity
    0.06
    vien
    0.06
    æģĭ
    0.06
    Activations Density 0.019%

    No Known Activations