© 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. 39055
    Prev
    Next
    INDEX
    Explanations

    known art

    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
    åĬłæĭ¿å¤§
    -0.11
    æĸ°åĬłåĿ¡
    -0.10
    æ¯Ľæ³½ä¸ľæĢĿæĥ³
    -0.08
    éĺ¿æĭī伯
    -0.08
    arily
    -0.07
    俱ä¹IJéĥ¨
    -0.07
    alih
    -0.07
    ikko
    -0.07
    两åѦä¸Ģåģļ
    -0.07
    ìĿĺ
    -0.07
    POSITIVE LOGITS
    ness
    0.09
    ìĤ¬íķŃ
    0.09
    mente
    0.09
    à§įà¦ŀ
    0.09
    ly
    0.08
     spann
    0.08
    re
    0.08
    ä¸Ģ个
    0.08
    ر
    0.07
     ìĤ¬íķŃ
    0.07
    Activations Density 0.001%

    No Known Activations