© 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. 56786
    Prev
    Next
    INDEX
    Explanations

    mathematical notation 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
    feh
    -0.08
    cs
    -0.08
    rad
    -0.07
    inde
    -0.07
    ÙİعÙĴ
    -0.06
    athan
    -0.06
    ä¹ĭåīįå°±
    -0.06
    _AG
    -0.06
     Agust
    -0.06
    ):(
    -0.06
    POSITIVE LOGITS
    åħ¶ä¸Ń
    0.09
    irut
    0.08
     Yorker
    0.07
    åĨķ
    0.07
    ucky
    0.07
    ubin
    0.07
    纫
    0.07
     Bakal
    0.07
     ÙħÙĨاÙģ
    0.07
    [,
    0.07
    Activations Density 0.019%

    No Known Activations