© 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. 62901
    Prev
    Next
    INDEX
    Explanations

    diamond

    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
    мп
    -0.08
    ìĿij
    -0.08
    nings
    -0.07
    ัà¸Ļà¸ĺà¹Į
    -0.07
    oa
    -0.07
    #
    -0.07
    mise
    -0.07
    æ³Ĭ
    -0.07
    ToFile
    -0.07
    ump
    -0.06
    POSITIVE LOGITS
    idium
    0.08
    ÙĪارÙĩ
    0.08
    -shaped
    0.08
    iewicz
    0.08
    iamond
    0.07
    fish
    0.07
    обÑĢаз
    0.07
    ique
    0.07
    æīĢæľīèĢħæĿĥçĽĬ
    0.07
    oidal
    0.07
    Activations Density 0.008%

    No Known Activations