© 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. 44691
    Prev
    Next
    INDEX
    Explanations

    global context and attributes

    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
    ä¹ĭ乡
    -0.10
    -gallery
    -0.09
    eln
    -0.09
    ebet
    -0.09
    累累
    -0.09
    年头
    -0.09
    chte
    -0.08
    -taking
    -0.08
    athom
    -0.08
    çīĩæľº
    -0.08
    POSITIVE LOGITS
    ized
    0.11
    ization
    0.10
    izing
    0.09
    /global
    0.09
    isation
    0.09
    ity
    0.09
    /local
    0.09
    -ish
    0.09
    mente
    0.09
    ize
    0.09
    Activations Density 0.024%

    No Known Activations