© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 62026
    Prev
    Next
    INDEX
    Explanations

    expectancy, age, year, mortality, coefficient

    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
    вÑĢи
    -0.07
     rác
    -0.07
    æŃ£å¤§
    -0.07
    ÑĤоÑĢин
    -0.07
     vali
    -0.07
     docking
    -0.07
    ÑĢил
    -0.07
     Reifen
    -0.07
    еÑģпе
    -0.07
    å°¾çĽĺ
    -0.07
    POSITIVE LOGITS
    callable
    0.08
     morb
    0.08
     mortality
    0.08
    çĻ¾å²ģ
    0.07
     frail
    0.07
    æĻĵ彤
    0.07
     Schedule
    0.07
    -death
    0.07
    æŃ»äº¡
    0.07
     callable
    0.07
    Activations Density 0.009%

    No Known Activations