© 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. 37449
    Prev
    Next
    INDEX
    Explanations

    communication

    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
    imize
    -0.08
    é«ĺçħ§
    -0.07
    iger
    -0.07
    hood
    -0.07
    bens
    -0.07
    ENCY
    -0.07
    -0.07
    uates
    -0.07
    dene
    -0.06
    eger
    -0.06
    POSITIVE LOGITS
    unication
    0.13
    ä¸įçķħ
    0.10
    มวลà¸Ĭà¸Ļ
    0.10
    -intensive
    0.09
    ercial
    0.08
    rades
    0.08
    asikan
    0.08
    /email
    0.08
    UNICATION
    0.08
    белÑĮ
    0.08
    Activations Density 0.048%

    No Known Activations