© 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. 57485
    Prev
    Next
    INDEX
    Explanations

    list/queue operations

    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
    uan
    -0.08
    lear
    -0.08
    вÑı
    -0.08
    ØŃÙĬØ©
    -0.07
    åĽŀ访
    -0.07
    ÙĪÙħÛĮ
    -0.07
    irectory
    -0.07
    çİĭä¼Ł
    -0.07
    weiler
    -0.07
    upes
    -0.07
    POSITIVE LOGITS
     uns
    0.08
    antin
    0.07
    uns
    0.07
    UNS
    0.07
    èĪŀ
    0.07
    eden
    0.07
    èĺ
    0.07
    jul
    0.06
    ants
    0.06
    è¯
    0.06
    Activations Density 0.016%

    No Known Activations