© 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. 56479
    Prev
    Next
    INDEX
    Explanations

    supposed to be

    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
    à¹īวย
    -0.09
    cek
    -0.07
    _arguments
    -0.07
    æĤ¨çļĦè¯Ħ论
    -0.07
    缩
    -0.07
    .testing
    -0.07
    edBy
    -0.07
     contohnya
    -0.07
    AtPath
    -0.07
    AVED
    -0.07
    POSITIVE LOGITS
    åľ¨æīĢ
    0.08
    åı¸
    0.08
    adam
    0.07
    ä¸įèĢĥèĻij
    0.07
    æķħæѤ
    0.07
    erg
    0.07
    abouts
    0.06
    statt
    0.06
    tright
    0.06
    quel
    0.06
    Activations Density 0.003%

    No Known Activations