© 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. 24824
    Prev
    Next
    INDEX
    Explanations

    words following certain phrases

    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
     appunto
    -0.13
    å®ĥä¸įä»ħ
    -0.08
    วà¹Īามัà¸Ļ
    -0.08
    æĺ¯åħ¶
    -0.07
    让å®ĥ
    -0.07
    ä»ħæıIJä¾Ľä¿¡æģ¯
    -0.07
    åħ¶çľŁå®ŀæĢ§
    -0.07
     satunya
    -0.07
     ÙĪاÙĦتÙĬ
    -0.07
     thereof
    -0.07
    POSITIVE LOGITS
     übrigens
    0.13
     inilah
    0.11
     обаÑĩе
    0.10
    ãģĮãģĵãģ®
    0.09
    æīĢæľīè¿ĻäºĽ
    0.09
    çļĦè¿ĻäºĽ
    0.09
     destas
    0.09
    对è¿ĻäºĽ
    0.09
     tehát
    0.09
    åľ¨è¿ĻäºĽ
    0.09
    Activations Density 1.829%

    No Known Activations