© 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. 35010
    Prev
    Next
    INDEX
    Explanations

    presence of "there is"

    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
    ster
    -0.08
    Ú¯ÛĮر
    -0.08
    riad
    -0.07
    磶
    -0.07
    umé
    -0.07
    Exited
    -0.07
    ÙĬÙĬÙĨ
    -0.07
    ifecycle
    -0.07
    Č↵
    -0.07
    êmes
    -0.07
    POSITIVE LOGITS
    åŃĺåľ¨çĿĢ
    0.08
     there
    0.08
    人æĺ¯
    0.08
    人æľī
    0.08
    assert
    0.07
     bahwa
    0.07
    ows
    0.07
     constat
    0.07
     There
    0.07
    There
    0.06
    Activations Density 0.047%

    No Known Activations