© 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. 29296
    Prev
    Next
    INDEX
    Explanations

    punctuation or code separators

    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
    и
    -0.09
    ات
    -0.08
    اÙĨÙĬ
    -0.08
    ìĿĦ
    -0.07
    ersistence
    -0.07
    çļĦ
    -0.07
    ãĥ¼ãĥ³
    -0.07
    ãĥ¼
    -0.07
    اÙĨÙĬØ©
    -0.07
    Õ¡Õ¶
    -0.07
    POSITIVE LOGITS
    oop
    0.09
    Ĥ
    0.09
    ìį¨
    0.08
    foundland
    0.08
    ikov
    0.08
    à¯įà®ķ
    0.08
    ik
    0.08
    0.08
    жай
    0.08
     undermin
    0.08
    Activations Density 0.003%

    No Known Activations