© 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. 17969
    Prev
    Next
    INDEX
    Explanations

    developing countries

    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
    akup
    -0.09
    enko
    -0.08
    ä½ķçŃī
    -0.07
    leger
    -0.07
    ekh
    -0.07
    æ±ķ
    -0.07
    amente
    -0.07
    Kho
    -0.07
    åĸĦæĦı
    -0.07
     Sindic
    -0.07
    POSITIVE LOGITS
    æľįåĬ¡åŀĭ
    0.08
    åŀĭ
    0.07
    ras
    0.07
    irl
    0.07
    ccio
    0.07
    iterate
    0.07
    æĪĸéĥ¨åĪĨ
    0.06
    essem
    0.06
    åľ°åĮºçļĦ
    0.06
     whose
    0.06
    Activations Density 0.178%

    No Known Activations