© 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. 3679
    Prev
    Next
    INDEX
    Explanations

    production, consumption, and rates

    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
    è´¸æĺĵæľīéĻIJåħ¬åı¸
    -0.07
    ä¹ĥèĩ³
    -0.07
    ä¸Ŀ绸ä¹ĭè·¯
    -0.06
    _LOADED
    -0.06
    .cgi
    -0.06
    -bot
    -0.06
     baile
    -0.06
    åŃ¦å£«
    -0.06
    ç¹ŀ
    -0.06
     toolkit
    -0.06
    POSITIVE LOGITS
     perv
    0.09
    ellik
    0.08
     prolific
    0.08
    loc
    0.08
    veh
    0.08
    åĮºåŁŁåĨħçļĦ
    0.08
    ä¸Ģ代
    0.07
    åĮºåŁŁåĨħ
    0.07
    rate
    0.07
    sink
    0.07
    Activations Density 0.011%

    No Known Activations