© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 37495
    Prev
    Next
    INDEX
    Explanations

    Buddleja alternifolia

    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
    Negative Logits
    bow
    -0.08
    åį¡ç½Ĺ
    -0.07
    çļĦæŶåĢĻäºĨ
    -0.07
    æĻ¨æĬ¥
    -0.07
    çļĦåŁºæľ¬åİŁåĪĻ
    -0.07
    енок
    -0.07
    ebra
    -0.07
    intai
    -0.07
    åı½
    -0.07
    usak
    -0.07
    POSITIVE LOGITS
    Âł
    0.08
    aven
    0.08
    ê°ķ
    0.07
    åºŃ
    0.07
    å¨ģ
    0.07
    guan
    0.07
    人以
    0.06
    rus
    0.06
    .addColumn
    0.06
    æģIJ
    0.06
    Activations Density 0.030%

    No Known Activations