© 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. 12707
    Prev
    Next
    INDEX
    Explanations

    URLs and technical explanations

    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
    igny
    -0.07
    elry
    -0.07
    æľīéģĵ
    -0.07
    velt
    -0.06
    bara
    -0.06
    ẩu
    -0.06
    éĢļè¿ĩåIJİ
    -0.06
    鼶è·Ŀ离
    -0.06
    åĩłç»ı
    -0.06
    Ø·ÙĬÙĨ
    -0.06
    POSITIVE LOGITS
     REN
    0.08
    iterations
    0.07
    ë°ĺ
    0.07
    iterate
    0.07
    odin
    0.07
     mutu
    0.07
    _repeat
    0.07
    esis
    0.07
     implicated
    0.06
    èij¡
    0.06
    Activations Density 0.001%

    No Known Activations