© 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. 60127
    Prev
    Next
    INDEX
    Explanations

    glaucoma therapy progression exposure

    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
    /provider
    -0.07
     stretching
    -0.07
    æľīäºĭ
    -0.06
    é¢łåĢĴ
    -0.06
    orca
    -0.06
    loading
    -0.06
    ĩ
    -0.06
    解åĨ»
    -0.06
    orÃŃa
    -0.06
    isson
    -0.06
    POSITIVE LOGITS
    arrer
    0.08
     اÙĦÙĩد
    0.08
    æĹ¥åIJij
    0.08
     recorr
    0.08
    _INS
    0.08
     Tanger
    0.08
    Unicode
    0.08
    çĸ®
    0.07
    -pages
    0.07
    èªĵ
    0.07
    Activations Density 0.003%

    No Known Activations