© 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. 23443
    Prev
    Next
    INDEX
    Explanations

    expects or expect

    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
     enje
    -0.08
    ikal
    -0.08
    -fetch
    -0.08
    quist
    -0.07
     tempt
    -0.07
    inu
    -0.07
    ifetime
    -0.07
    /of
    -0.07
    ặn
    -0.07
     logÃŃstica
    -0.07
    POSITIVE LOGITS
    ä½Ĩä¸įéĻIJäºİ
    0.11
    ÏĦαι
    0.08
     a
    0.08
    ä½łæĬĬ
    0.07
     us
    0.07
    ably
    0.07
     to
    0.07
    à¸ģาร
    0.07
    à¸ģารà¸Īัà¸Ķà¸ģาร
    0.07
     answers
    0.07
    Activations Density 0.008%

    No Known Activations