© 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. 45819
    Prev
    Next
    INDEX
    Explanations

    capitalization changes

    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
    elay
    -0.07
    ứ
    -0.07
    å¦ĤåĽł
    -0.07
    æĹ·
    -0.06
    serter
    -0.06
    urato
    -0.06
    å¦Ĥ对
    -0.06
    æ¯ıå¼ł
    -0.06
    uite
    -0.06
    ç®Ģ约
    -0.06
    POSITIVE LOGITS
     lowercase
    0.11
    .capitalize
    0.10
    capitalize
    0.09
     capitalize
    0.09
     strtolower
    0.08
    ona
    0.08
    é²ľèĤī
    0.08
    -capital
    0.08
    ohn
    0.08
    åıįå·®
    0.08
    Activations Density 0.019%

    No Known Activations