© 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. 27664
    Prev
    Next
    INDEX
    Explanations

    mortality rate

    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
    æľĢ大åĬŁçİĩ
    -0.07
     ÑĥÑĤÑĢа
    -0.07
    contents
    -0.07
     maxHeight
    -0.07
     vibrating
    -0.06
    ynn
    -0.06
    shore
    -0.06
    _contents
    -0.06
    éĵ¶å±±
    -0.06
    yt
    -0.06
    POSITIVE LOGITS
     rates
    0.15
    çİĩåľ¨
    0.14
    çİĩåĴĮ
    0.14
    çİĩ
    0.14
     rate
    0.14
    çİĩ为
    0.13
    -rate
    0.13
    çİĩçļĦ
    0.13
    çİĩé«ĺ
    0.12
     Rates
    0.12
    Activations Density 0.401%

    No Known Activations