© 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. 28258
    Prev
    Next
    INDEX
    Explanations

    number followed by => or ]

    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
    ==
    -0.07
    äºİ
    -0.06
    äºİè¡Į
    -0.06
    enius
    -0.06
    ÑĢази
    -0.06
    номи
    -0.06
    uit
    -0.06
    Ñģе
    -0.06
    orca
    -0.06
    orro
    -0.06
    POSITIVE LOGITS
    رج
    0.08
    ä¸Ń磩
    0.08
    _MAXIMUM
    0.07
    ayangkan
    0.07
    afone
    0.07
    áž
    0.07
    aday
    0.07
    ellem
    0.07
    AGMA
    0.07
    fonds
    0.07
    Activations Density 0.013%

    No Known Activations