© 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. 60723
    Prev
    Next
    INDEX
    Explanations

    vacation and browsing

    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
    éĹ®é¢ĺçļĦèĥ½åĬĽ
    -0.08
    verd
    -0.08
    chand
    -0.08
    çĥ
    -0.07
    IfExists
    -0.07
    婧
    -0.07
    ׼×ķ
    -0.07
    è¿ĺæľīå¾ħ
    -0.07
    åľ¨è¿Ļ段æŶéĹ´
    -0.07
     olas
    -0.07
    POSITIVE LOGITS
    æŶåıijçİ°
    0.10
    ä¸Ńåıijçİ°
    0.10
    ä¸įå°ıå¿ĥ
    0.09
    ä¸įæħİ
    0.08
    éłĨ便
    0.08
     accidentally
    0.08
    æĹ¶è¢«
    0.08
    éļĽãģ«
    0.07
    顺便
    0.07
    ä¹ĭæľº
    0.07
    Activations Density 0.362%

    No Known Activations