© 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. 1074
    Prev
    Next
    INDEX
    Explanations

    "nor"

    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
    opa
    -0.07
    ÙħÙĨت
    -0.06
    appa
    -0.06
    顾ä¸įä¸Ĭ
    -0.06
    aunch
    -0.06
    ")->
    -0.06
    oose
    -0.06
     aant
    -0.06
    OSE
    -0.06
     (>
    -0.06
    POSITIVE LOGITS
     nor
    0.10
    ä¹Łæ²¡æľī
    0.09
    Nor
    0.08
    ä¹Łä¸įçŁ¥éģĵ
    0.08
    åĽ¾çīĩæĪĸ
    0.08
     Nor
    0.08
    éĿŀè¦ģ
    0.08
    å¤įåĪ¶æĪĸ
    0.08
    urb
    0.07
    ä¹Łæ²¡
    0.07
    Activations Density 0.020%

    No Known Activations