© 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. 24913
    Prev
    Next
    INDEX
    Explanations

    hyperglycemia, pH, antibodies, pollution, damage

    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
    pira
    -0.07
    éĢłç¦ı
    -0.07
    页第
    -0.07
    olina
    -0.07
    менÑĥ
    -0.07
    ä¸įä¼ļ被
    -0.07
    ä¸Ģ鸣
    -0.07
    iants
    -0.07
    åĪ¶å®ļ
    -0.06
     minh
    -0.06
    POSITIVE LOGITS
    æݥ踵
    0.09
    导èĩ´çļĦ
    0.08
    -induced
    0.08
     สà¹Īà¸ĩà¸ľà¸¥
    0.08
    çļĦåĪ°æĿ¥
    0.08
    导èĩ´
    0.08
     Figu
    0.08
    olio
    0.07
    缴æİ¥æĪĸéĹ´æİ¥
    0.07
    çŃīåİŁåĽł
    0.07
    Activations Density 0.063%

    No Known Activations