© 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. 1265
    Prev
    Next
    INDEX
    Explanations

    simple

    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
    æ¯Ķè¾ĥå¤įæĿĤ
    -0.08
    çī¹éĴ¢
    -0.07
    ä¸Ģå®ļè¦ģæľī
    -0.07
     parcialmente
    -0.07
    æľīæĿ¡ä»¶çļĦ
    -0.07
    æĺ¯ç»ıè¿ĩ
    -0.07
    anns
    -0.06
    Ľ°
    -0.06
    ä¸įæĺ¯åĽłä¸º
    -0.06
    ouser
    -0.06
    POSITIVE LOGITS
    ç®ĢåįķçļĦ
    0.27
     simple
    0.27
    ç®Ģåįķ
    0.25
    å¾Īç®Ģåįķ
    0.24
    simple
    0.23
    æľĢç®Ģåįķ
    0.23
     simplest
    0.22
     Simple
    0.22
    æľĢç®ĢåįķçļĦ
    0.22
     simplicity
    0.22
    Activations Density 0.447%

    No Known Activations