© 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. 8911
    Prev
    Next
    INDEX
    Explanations

    code structure or constructs

    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
    éºŁ
    -0.08
    iffin
    -0.07
    .writeln
    -0.06
    urin
    -0.06
    UIL
    -0.06
     (<
    -0.06
    æĮŁ
    -0.06
    ashian
    -0.06
    uton
    -0.06
     accro
    -0.06
    POSITIVE LOGITS
     _)
    0.08
    ÕĢ
    0.08
    opsy
    0.08
    zilla
    0.07
    HONE
    0.07
    tige
    0.07
    æĸ¹
    0.07
    ìłĦìĹIJìĦľ
    0.07
    温
    0.07
    eking
    0.07
    Activations Density 0.091%

    No Known Activations