© 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. 19847
    Prev
    Next
    INDEX
    Explanations

    web programming & academic terms

    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
    chino
    -0.07
    زÙĪ
    -0.07
    ä¸ĭä¸ĢåĪ»
    -0.07
    parti
    -0.07
    éĢģä¸Ĭ
    -0.07
    ÙĬÙĨÙĪ
    -0.07
    astian
    -0.07
    chado
    -0.07
    AsString
    -0.07
    æł·
    -0.07
    POSITIVE LOGITS
    erot
    0.07
    áĥĽáĥIJ
    0.07
    hack
    0.07
    å°ıé¢ĺ
    0.07
    uft
    0.07
    ut
    0.06
    æĪ·æĪ·
    0.06
    au
    0.06
    æ¿Ģ
    0.06
    ×¢×ķת
    0.06
    Activations Density 0.014%

    No Known Activations