© 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. 60240
    Prev
    Next
    INDEX
    Explanations

    scientific and medical 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
    ä»Ģä¹Īåij¢
    -0.08
    olino
    -0.07
    æŁIJç§įç¨ĭ度ä¸Ĭ
    -0.06
    滨河
    -0.06
    ediye
    -0.06
    ellino
    -0.06
    çļĦå¿ĥéĩĮ
    -0.06
    ç«ĭå¿Ĺ
    -0.06
    пÑĢоÑĩем
    -0.06
    顾åIJįæĢĿ
    -0.06
    POSITIVE LOGITS
    å¿ł
    0.07
    ffy
    0.07
    िता
    0.07
    ×ij×ķר
    0.06
    NIL
    0.06
    borg
    0.06
    åīįèĢħ
    0.06
    ³
    0.06
    //"
    0.06
    cita
    0.06
    Activations Density 0.464%

    No Known Activations