© 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. 22189
    Prev
    Next
    INDEX
    Explanations

    names of places

    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
    zeci
    -0.07
    ainte
    -0.07
    èľ¿
    -0.06
     Foster
    -0.06
    ercul
    -0.06
    çĤĬ
    -0.06
    ãĥ¼ãĤ¿
    -0.06
    潺
    -0.06
    в
    -0.06
    åĬłåĭĴ
    -0.06
    POSITIVE LOGITS
    òi
    0.08
    æ°ı
    0.08
    éĽĨåĽ¢åľ¨
    0.08
    æķĻæİĪçļĦ
    0.08
    æĢĿ
    0.08
    ucha
    0.08
    âĵĴ
    0.08
    æĸĮ
    0.08
    éĽĨåĽ¢æĹĹä¸ĭ
    0.07
    ç¥ĸ
    0.07
    Activations Density 2.384%

    No Known Activations