© 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. 63128
    Prev
    Next
    INDEX
    Explanations

    new or existing data

    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
     beis
    -0.08
    .tw
    -0.07
    èĭ±æĸĩåIJį称
    -0.07
    Į¨
    -0.07
    aeda
    -0.07
    reon
    -0.07
    æĽĻ
    -0.07
    ymology
    -0.07
    年建
    -0.07
    γκ
    -0.07
    POSITIVE LOGITS
    _exclude
    0.08
    æijĩæijĩ
    0.06
    erville
    0.06
    纱
    0.06
    istream
    0.06
    æĻĥ
    0.06
    åijľåijľ
    0.06
     mast
    0.06
    las
    0.06
    Manip
    0.06
    Activations Density 0.001%

    No Known Activations