© 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. 63318
    Prev
    Next
    INDEX
    Explanations

    numbers and time duration

    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
    ...**
    -0.07
    vier
    -0.06
    iy
    -0.06
    âĢ¦**
    -0.06
    //:
    -0.06
    ”âĢ¦
    -0.06
    âĢ¦*
    -0.06
    ).-
    -0.06
    -ci
    -0.06
    ä¸Ĭåīį
    -0.06
    POSITIVE LOGITS
     conservatism
    0.07
    odem
    0.07
    ä¸Ŀ毫ä¸į
    0.07
    ändigen
    0.07
     trúc
    0.07
    gewater
    0.07
    æĹıèĩªæ²»å·ŀ
    0.07
    resentation
    0.07
    olph
    0.06
    æīĽ
    0.06
    Activations Density 0.012%

    No Known Activations