© 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. 59873
    Prev
    Next
    INDEX
    Explanations

    numbers followed by punctuation

    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
    lobal
    -0.07
    bras
    -0.07
    ear
    -0.07
    RAS
    -0.07
    å·¦åı³
    -0.07
    beck
    -0.07
    达产年
    -0.07
    à¦ļার
    -0.07
    iban
    -0.06
    æĹ¶èµ·
    -0.06
    POSITIVE LOGITS
    认
    0.07
     exposes
    0.07
    èħº
    0.07
    etés
    0.07
     eject
    0.07
     duo
    0.06
     structural
    0.06
     STDOUT
    0.06
    åĴ¨
    0.06
    ä¸Ģ声
    0.06
    Activations Density 0.055%

    No Known Activations