© 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. 2323
    Prev
    Next
    INDEX
    Explanations

    administrative law and functions

    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
    รà¹Į
    -0.07
    urance
    -0.07
    (mi
    -0.06
    Ú¯ÛĮر
    -0.06
    edException
    -0.06
    пÑĢÑı
    -0.06
    re
    -0.06
    tene
    -0.06
    ffee
    -0.06
    rame
    -0.06
    POSITIVE LOGITS
    زاÙĨ
    0.09
    amenta
    0.09
    åĴĮ社åĮº
    0.08
    ấp
    0.08
    ä¸ĢåĽŀäºĭ
    0.08
    antil
    0.08
    uyo
    0.08
    ooter
    0.08
    볬
    0.07
    gone
    0.07
    Activations Density 0.004%

    No Known Activations