© 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. 2170
    Prev
    Next
    INDEX
    Explanations

    web addresses

    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
    ä½Ĩä¸įéĻIJäºİ
    -0.13
    人
    -0.12
    à¸ģาร
    -0.12
    ÛĮ
    -0.12
    äºĨ
    -0.11
    Ùĩ
    -0.11
    对
    -0.11
    ä¸Ģ个
    -0.10
    ÑģÑı
    -0.10
    اÙĨ
    -0.10
    POSITIVE LOGITS
    -fashioned
    0.09
    chy
    0.09
    abler
    0.09
    ignal
    0.09
    üt
    0.08
    resenter
    0.08
    icina
    0.08
    ses
    0.08
    jen
    0.08
    aic
    0.08
    Activations Density 0.002%

    No Known Activations