© 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. 51070
    Prev
    Next
    INDEX
    Explanations

    closing 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
    oles
    -0.07
    éal
    -0.07
    irit
    -0.07
    AFX
    -0.07
    åIJĪåIJĮæŶ
    -0.07
    éĺ¿
    -0.06
    åı¸
    -0.06
    seiten
    -0.06
    pekt
    -0.06
    usu
    -0.06
    POSITIVE LOGITS
    妩
    0.07
    volo
    0.07
    uest
    0.07
    ÑĢож
    0.06
    ứ
    0.06
    ä¸Ģä¸ĭåŃIJå°±
    0.06
    bolo
    0.06
    èį·
    0.06
    ä¸Ģä¸ĭå°±
    0.06
    éĿ¢ä¸ĬçļĦ
    0.06
    Activations Density 0.209%

    No Known Activations