© 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. 54967
    Prev
    Next
    INDEX
    Explanations

    weeks of age

    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
    avel
    -0.08
    æĹ¥æŃ¢
    -0.07
    roma
    -0.07
    è¿Ħ
    -0.06
    åķ
    -0.06
    åѦåı²
    -0.06
    appen
    -0.06
    ymar
    -0.06
    pron
    -0.06
     Hen
    -0.06
    POSITIVE LOGITS
    ectos
    0.08
    æ´ŀ
    0.07
    ìĩĦ
    0.07
    à¹Ģà¸Ķà¸Ĭ
    0.07
     Repository
    0.07
     somew
    0.07
    西æŀĹ
    0.07
    åĵº
    0.07
    éĻ
    0.07
    缨
    0.07
    Activations Density 0.120%

    No Known Activations