© 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. 20959
    Prev
    Next
    INDEX
    Explanations

    mathematical difference in code

    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
    oyer
    -0.08
    thur
    -0.08
    çļĦè¿ĺæĺ¯
    -0.08
    gelt
    -0.07
    åı¦å¤ĸä¸Ģ个
    -0.07
     Doming
    -0.07
    alic
    -0.07
    åŁİ西
    -0.07
    zier
    -0.07
    _SIGNATURE
    -0.07
    POSITIVE LOGITS
    æĤ¬æ®Ĭ
    0.07
    asten
    0.07
    ìĦŃ
    0.07
    åıªå·®
    0.07
    ologne
    0.06
    :num
    0.06
    á»ĩ
    0.06
     вле
    0.06
     difference
    0.06
    ¾
    0.06
    Activations Density 0.005%

    No Known Activations