© 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. 51558
    Prev
    Next
    INDEX
    Explanations

    medication dosage amounts

    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
    _DECLARE
    -0.07
    æŃĩ
    -0.07
    abin
    -0.07
    æĦıæĸĻ
    -0.07
    ilities
    -0.07
    æĭĽèģĺèģĮä½į
    -0.07
     tighter
    -0.07
    ç´§å¯Ĩ
    -0.07
    iez
    -0.06
    èĥŀèĥİ
    -0.06
    POSITIVE LOGITS
     doses
    0.12
    åīĤéĩı
    0.11
    æĪIJ人
    0.10
     dosage
    0.10
     dose
    0.09
    æ¯ı人
    0.09
    çĶ¨éĩı
    0.09
     Adults
    0.09
     adults
    0.09
    èµ·æŃ¥
    0.09
    Activations Density 0.153%

    No Known Activations