© 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. 12768
    Prev
    Next
    INDEX
    Explanations

    timely actions

    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
    rient
    -0.08
    ation
    -0.08
    ç«ĭå¿Ĺ
    -0.07
    Ĺ
    -0.07
    sWith
    -0.07
    str
    -0.07
    à§Ģয়
    -0.07
    à¥įड
    -0.07
    è¯Ńè¨ĢæĸĩåѦ
    -0.07
    alise
    -0.07
    POSITIVE LOGITS
    ly
    0.11
    aneously
    0.10
    à¸Ĺัà¸Ļ
    0.10
    íŀĪ
    0.09
    足é¢Ŀ
    0.09
    åıĬæŶçļĦ
    0.09
    åľ°åIJij
    0.08
    erness
    0.08
    aneous
    0.08
    髦
    0.08
    Activations Density 0.012%

    No Known Activations