© 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. 40353
    Prev
    Next
    INDEX
    Explanations

    the same

    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
     mes
    -0.08
    è·Łäºº
    -0.08
    寡
    -0.07
     sort
    -0.06
    skr
    -0.06
    åľ¨äºº
    -0.06
    hov
    -0.06
    mes
    -0.06
    æĦıåIJij
    -0.06
    ä¸Ģå®ļç¨ĭ度ä¸Ĭ
    -0.06
    POSITIVE LOGITS
    quista
    0.08
    dart
    0.08
    ugu
    0.08
     }>
    0.08
    vand
    0.07
    embl
    0.07
    usan
    0.07
    _FA
    0.07
    大æĪı
    0.07
     bara
    0.06
    Activations Density 0.006%

    No Known Activations