© 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. 13799
    Prev
    Next
    INDEX
    Explanations

    When are

    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
    ä¸Ĭ大
    -0.07
    ses
    -0.07
    nt
    -0.07
    acman
    -0.07
    ips
    -0.07
    ä¸Ĭå°Ĩ
    -0.07
    liste
    -0.06
    ลัà¸ĩ
    -0.06
     populous
    -0.06
    fred
    -0.06
    POSITIVE LOGITS
    ColumnType
    0.08
    °
    0.08
    chado
    0.08
    )object
    0.07
    天å¿ĥ
    0.07
     déb
    0.07
    anita
    0.07
    /edit
    0.06
    ilage
    0.06
    &type
    0.06
    Activations Density 0.001%

    No Known Activations