© 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. 20748
    Prev
    Next
    INDEX
    Explanations

    timestamps, dates, and times

    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
    iban
    -0.08
    tober
    -0.07
    åį³æĹ¥èµ·èĩ³
    -0.07
    heits
    -0.07
    ĥ½
    -0.07
    姿
    -0.07
    alista
    -0.07
    ocol
    -0.07
    hart
    -0.07
    µľ
    -0.07
    POSITIVE LOGITS
    anas
    0.07
    俱åħ¨
    0.07
     //!
    0.07
    ãģIJãĤĭ
    0.07
    olute
    0.06
     Guardia
    0.06
    OwnProperty
    0.06
    UTC
    0.06
    æ¯ıæľŁ
    0.06
    elapsed
    0.06
    Activations Density 0.013%

    No Known Activations