© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 32704
    Prev
    Next
    INDEX
    Explanations

    larger, bigger, large

    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
    Not in Any Lists

    No Comments

    Negative Logits
    æĹłåĩł
    -0.08
     Everywhere
    -0.07
    è´±
    -0.07
    çļĦå°ı鸣
    -0.07
    è½»
    -0.07
    çģµåĬ¨
    -0.07
    åıįè¦Ĩ
    -0.07
    welt
    -0.07
     tight
    -0.07
    éĶIJ
    -0.07
    POSITIVE LOGITS
    çŃī大åŀĭ
    0.20
     larger
    0.20
     bigger
    0.18
     large
    0.18
    çļĦ大åŀĭ
    0.18
     Larger
    0.17
    Large
    0.17
    大åŀĭ
    0.17
    large
    0.17
    à¸Ĥà¸Ļาà¸Ķà¹ĥหà¸įà¹Ī
    0.17
    Activations Density 1.180%

    No Known Activations