© 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. 43425
    Prev
    Next
    INDEX
    Explanations

    already seen or tried

    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
    æĽ´åĬłæĸ¹ä¾¿
    -0.07
    teman
    -0.06
    æĻ¶æĻ¶
    -0.06
     simultaneously
    -0.06
    å·§
    -0.06
    etr
    -0.06
    ÙĬÙĤ
    -0.06
    .monitor
    -0.06
     вовÑģе
    -0.06
     Klar
    -0.06
    POSITIVE LOGITS
     already
    0.11
     Already
    0.11
    Already
    0.11
    人已
    0.10
     alred
    0.10
    already
    0.10
    å·²ç»ıå°Ĩ
    0.10
    å·²åľ¨
    0.09
    她已ç»ı
    0.09
    ä»ĸå·²ç»ı
    0.09
    Activations Density 0.058%

    No Known Activations