© 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. 20139
    Prev
    Next
    INDEX
    Explanations

    codimensional, maximal subgroup, interpolation, hyperplane, astatic, esium Mod

    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
    джи
    -0.08
    ificazione
    -0.08
    ilan
    -0.07
    anium
    -0.07
    æĭĨ解
    -0.07
    ernas
    -0.07
     forwards
    -0.07
    à¸Īริà¸ķ
    -0.07
    çªģé£ŀ
    -0.07
    æīĵ人
    -0.06
    POSITIVE LOGITS
    çİĭæĢĿ
    0.07
    失
    0.07
    .intValue
    0.07
    issing
    0.07
    nitz
    0.07
    Lint
    0.07
    åľ¨å¤§
    0.07
     major
    0.06
    raft
    0.06
    ä¸ĢçŃī
    0.06
    Activations Density 0.002%

    No Known Activations