© 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. 26959
    Prev
    Next
    INDEX
    Explanations

    special characters before comments or keywords

    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
    ¨
    -0.08
    steen
    -0.07
    inho
    -0.07
    çļĦä¸įæĺ¯
    -0.07
    otoxic
    -0.06
    ugn
    -0.06
    uchar
    -0.06
    ovol
    -0.06
    cout
    -0.06
    asha
    -0.06
    POSITIVE LOGITS
    lia
    0.07
    ).-
    0.07
    enner
    0.07
    lian
    0.07
    áĥļáĥĿ
    0.06
    jabi
    0.06
    ãģĦ
    0.06
    ipper
    0.06
    avi
    0.06
    ilus
    0.06
    Activations Density 0.812%

    No Known Activations