© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 39814
    Prev
    Next
    INDEX
    Explanations

    bigint accommodation km

    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
    iali
    -0.08
    ial
    -0.08
    hold
    -0.08
    veau
    -0.07
     Directions
    -0.07
    å±Ĥé«ĺ
    -0.07
    rieben
    -0.07
    iale
    -0.07
    DOM
    -0.07
    ovich
    -0.07
    POSITIVE LOGITS
    رض
    0.07
     Winn
    0.07
    ابÙĬ
    0.06
    ç»Ļä¸İ
    0.06
    产
    0.06
    LOUD
    0.06
    ä½łåį´
    0.06
     bin
    0.06
    æļĸæļĸ
    0.06
    åIJİæİĴ
    0.06
    Activations Density 0.001%

    No Known Activations