© 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. 64113
    Prev
    Next
    INDEX
    Explanations

    signed a contract

    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
     Aleman
    -0.07
    ================================================================
    -0.07
     GmbH
    -0.07
    çIJĨæīĢ
    -0.07
    ç¨ĭ度çļĦ
    -0.07
    és
    -0.06
    imana
    -0.06
    awat
    -0.06
    _WE
    -0.06
     Tanah
    -0.06
    POSITIVE LOGITS
    acher
    0.07
    achers
    0.07
    peria
    0.07
    amen
    0.07
    kst
    0.07
    pages
    0.06
    ï½ŀãĢĤ
    0.06
    åŁİå¤ĸ
    0.06
    bai
    0.06
    pee
    0.06
    Activations Density 0.115%

    No Known Activations