© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 14940
    Prev
    Next
    INDEX
    Explanations

    ln(x) or ln{x}

    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
    rawl
    -0.07
    wiat
    -0.07
    enske
    -0.07
    irate
    -0.07
    çĹ´
    -0.07
    _FALSE
    -0.07
    apy
    -0.07
    ÑĢад
    -0.06
    olg
    -0.06
    .strict
    -0.06
    POSITIVE LOGITS
    axe
    0.07
    åĩ½
    0.07
    ÏĦιά
    0.07
    åıį対
    0.07
    ä¸½å¨ľ
    0.07
    ç¢į
    0.07
    :])
    0.07
    æŁ¥çľĭçŃĶæ¡Ī
    0.06
    对éĿ¢
    0.06
    æĹ¥æľŁéĹ´
    0.06
    Activations Density 0.002%

    No Known Activations