© 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. 38118
    Prev
    Next
    INDEX
    Explanations

    method definitions and code syntax

    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
    éma
    -0.08
    ä¿¡æģ¯åıĬ
    -0.07
    åĨħ容æľī
    -0.07
    amax
    -0.07
    åľ¨åħ¶ä¸Ń
    -0.07
     closure
    -0.07
    çĶŁæ´»åĵģè´¨
    -0.07
    设计åĩº
    -0.07
    erva
    -0.06
    nhard
    -0.06
    POSITIVE LOGITS
    ä¹Łåı¯ä»¥æĺ¯
    0.09
    缴æİ¥åħ³ç³»åĪ°
    0.07
    æ¯ķç«Łæĺ¯
    0.07
    ä¹Łåı¯èĥ½æĺ¯
    0.07
     eros
    0.07
     supposed
    0.07
    缴æݥ影åĵį
    0.07
    å¾Ĺåĥı
    0.07
    asal
    0.06
    кÑĨиÑı
    0.06
    Activations Density 0.007%

    No Known Activations