© 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. 4766
    Prev
    Next
    INDEX
    Explanations

    `.department` and `.name` labels

    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
    ¡
    -0.06
    åľ¨èģĮ
    -0.06
    æĿ¡æĿ¡
    -0.06
    âī
    -0.06
    app
    -0.06
    /
    -0.06
    ä½Ĩèĩ³å°ij
    -0.06
    ÑĢон
    -0.06
    nap
    -0.06
    /app
    -0.06
    POSITIVE LOGITS
    onymous
    0.10
    ieÅĦ
    0.08
    æľĪæ´»åĬ¨
    0.08
    trit
    0.08
    ertime
    0.08
    yscale
    0.07
    itial
    0.07
    iteDatabase
    0.07
    lobals
    0.07
     presta
    0.07
    Activations Density 0.014%

    No Known Activations