© 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. 33549
    Prev
    Next
    INDEX
    Explanations

    aquaporins and carbonic anhydrases

    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
    alap
    -0.07
    uet
    -0.07
    ogr
    -0.07
    çļĦä¸įèī¯
    -0.07
    éħįæĸĻ
    -0.07
    á»įng
    -0.07
    embers
    -0.07
    è¡ħ
    -0.07
    สุà¸Ķ
    -0.07
    鼻åŃIJåł±
    -0.07
    POSITIVE LOGITS
    -lined
    0.08
    çļĦå¿«éĢŁ
    0.07
    Speed
    0.07
    -mediated
    0.07
     speed
    0.07
    ephy
    0.07
    -filled
    0.07
     Speed
    0.06
    -equipped
    0.06
     Bren
    0.06
    Activations Density 0.010%

    No Known Activations