© 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. 44398
    Prev
    Next
    INDEX
    Explanations

    endpoint contexts

    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
    ivet
    -0.08
    ey
    -0.08
    à¸ĩ
    -0.08
    umente
    -0.08
    erve
    -0.08
    andum
    -0.07
    à¸Ĭีà¸ŀ
    -0.07
    cing
    -0.07
    fully
    -0.07
    cape
    -0.07
    POSITIVE LOGITS
    sWith
    0.10
    less
    0.09
    LESS
    0.09
    ä¹ĭä¸ĢçļĦ
    0.09
    åĴĮåĨħ容
    0.08
    yal
    0.08
    zysta
    0.08
    chaft
    0.08
    anjang
    0.08
    ÑģÑĮ
    0.08
    Activations Density 0.004%

    No Known Activations