© 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. 59047
    Prev
    Next
    INDEX
    Explanations

    missing, censored, tail, truncated data

    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
    æĭĽå¾ħ
    -0.07
    accio
    -0.07
    姻
    -0.07
    ëį°
    -0.07
     prik
    -0.07
    ulla
    -0.07
    ozo
    -0.07
    alez
    -0.06
    acht
    -0.06
    uld
    -0.06
    POSITIVE LOGITS
    æ¦Ĥçİĩ
    0.08
    æľįä»İ
    0.08
     probability
    0.07
    åī²
    0.07
    åģı
    0.07
    صØŃ
    0.07
    ammers
    0.07
     Statistics
    0.06
    æĪª
    0.06
    ä¸ĢåĪĢ
    0.06
    Activations Density 0.003%

    No Known Activations