© 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. 29640
    Prev
    Next
    INDEX
    Explanations

    shows 7

    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
    ä¹ĭåĪĹ
    -0.07
    æĸ¯é¡¿
    -0.07
    åºŁè¯Ŀ
    -0.07
    LayoutManager
    -0.07
    æĺ¯éĤ£
    -0.07
    âĸ·
    -0.07
    åĽłä¸ºè¿Ļ
    -0.07
    cko
    -0.07
    è¿Ļ段è¯Ŀ
    -0.07
    ä¸įçĪ½
    -0.07
    POSITIVE LOGITS
    æ··
    0.08
    æŃ£å¥½
    0.07
    acen
    0.07
    artal
    0.07
     Mixed
    0.07
     mixed
    0.07
    æ··åIJĪ
    0.07
     MIX
    0.06
    Mixed
    0.06
    èĻ½æľī
    0.06
    Activations Density 0.003%

    No Known Activations