© 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. 42413
    Prev
    Next
    INDEX
    Explanations

    immunisation coverage

    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
    %@
    -0.07
    .eth
    -0.07
    è´¯
    -0.07
     ׾׼׾
    -0.07
    alnych
    -0.06
    ]+)/
    -0.06
     íĸ¥
    -0.06
    貫
    -0.06
    宣
    -0.06
    æĸĮ
    -0.06
    POSITIVE LOGITS
     numerator
    0.09
    模æĭŁé¢ĺ
    0.08
     limp
    0.08
    æĮĸ
    0.08
    iby
    0.08
    类似éĹ®é¢ĺ
    0.07
    ebi
    0.07
    æĽ´å¤ļ精彩åĨħ容
    0.07
    æĸ°éĹ®é¢ĺ
    0.07
    ibun
    0.07
    Activations Density 0.011%

    No Known Activations