© 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. 56260
    Prev
    Next
    INDEX
    Explanations

    names of people

    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
    elpers
    -0.07
    Otherwise
    -0.07
    ÙĪÙī
    -0.07
    osto
    -0.07
    developers
    -0.07
    bey
    -0.07
    addin
    -0.07
    èĢĥéªĮ
    -0.07
    å¿ĹæĪIJ
    -0.07
    好åij¢
    -0.07
    POSITIVE LOGITS
    ju
    0.07
    ãģ¿
    0.07
    ãģ¿ãĤĦ
    0.06
    åħļ
    0.06
    ydd
    0.06
    åĪ°ä¸Ń
    0.06
    åĪ°æĻļ
    0.06
    åĩºèµĦæĹ¥æľŁ
    0.06
    ä¸Ģåľ°
    0.06
    lem
    0.06
    Activations Density 0.009%

    No Known Activations