© 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. 61800
    Prev
    Next
    INDEX
    Explanations

    numeric characters and code snippets

    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
    ³
    -0.08
    iblio
    -0.07
    leh
    -0.07
     itd
    -0.06
    ori
    -0.06
    åIJĮçŃī
    -0.06
    ossen
    -0.06
    ueva
    -0.06
    VERR
    -0.06
    λλη
    -0.06
    POSITIVE LOGITS
    lou
    0.07
    æį¢
    0.07
    ingles
    0.07
    ä¼Ĭå§ĭ
    0.07
    ãĢįãĢĮ
    0.07
    åĬ©
    0.07
     Hanna
    0.06
     плÑİÑģ
    0.06
    mium
    0.06
    ä¸İä¼Ĺ
    0.06
    Activations Density 0.029%

    No Known Activations