© 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. 61312
    Prev
    Next
    INDEX
    Explanations

    code structure comparison

    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
    cec
    -0.07
    niec
    -0.06
    .Bind
    -0.06
    ä¸į解
    -0.06
    使çĶ¨åIJİ
    -0.06
     Maggi
    -0.06
    _bind
    -0.06
     closure
    -0.06
    closure
    -0.06
     coincidence
    -0.06
    POSITIVE LOGITS
    交æį¢
    0.08
    ç½®æį¢
    0.08
    son
    0.07
     deserving
    0.07
     comparisons
    0.07
    prot
    0.07
    elter
    0.07
     Sorting
    0.07
    å¼Ĥä½į
    0.07
     sou
    0.07
    Activations Density 0.003%

    No Known Activations