© 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. 18089
    Prev
    Next
    INDEX
    Explanations

    special characters and code delimiters

    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
     Cafe
    -0.08
    awei
    -0.08
    æľ¬æ¥¼
    -0.08
    иÑĤоÑĢ
    -0.08
    /bus
    -0.07
    auer
    -0.07
    okr
    -0.07
    ebas
    -0.07
    [test
    -0.07
    女足
    -0.07
    POSITIVE LOGITS
    åł
    0.08
    麽
    0.07
    æĴ
    0.07
    Âł
    0.06
    çį
    0.06
    lipp
    0.06
    åŃ
    0.06
    è¿ĩåİ»
    0.06
    âĢİ
    0.06
    гÑĥÑĢ
    0.06
    Activations Density 1.357%

    No Known Activations