© 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. 40934
    Prev
    Next
    INDEX
    Explanations

    anniversary gift

    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
    åIJij被åijĬ
    -0.06
    asseur
    -0.06
    erty
    -0.06
    ÏģοÏĨο
    -0.05
    hx
    -0.05
    innerText
    -0.05
     ÙĦØ·
    -0.05
     nhẫn
    -0.05
    جÙħØ©
    -0.05
    ajah
    -0.05
    POSITIVE LOGITS
    ¯
    0.06
    баÑĢи
    0.06
    utato
    0.06
    bung
    0.05
    uve
    0.05
    utando
    0.05
    istentes
    0.05
    ูล
    0.05
    urin
    0.05
     célib
    0.05
    Activations Density 0.965%

    No Known Activations