© 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. 19503
    Prev
    Next
    INDEX
    Explanations

    mandated, mandatory, compulsory

    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
    åĻĮ
    -0.07
    auh
    -0.07
    ç¼ĵ
    -0.07
    ä½ĵåĴĮ
    -0.07
    aise
    -0.07
    ritto
    -0.07
    好ä¹ħ
    -0.07
    /cpp
    -0.07
    ä½ĵ
    -0.07
    ostat
    -0.07
    POSITIVE LOGITS
     mandated
    0.08
     mandatory
    0.07
    æĹ¢çĦ¶
    0.07
    å¾Ħ
    0.07
    åĽłæĤ¨çļĦ
    0.07
    chor
    0.07
    婪
    0.06
    odos
    0.06
     compulsory
    0.06
    éģµçħ§
    0.06
    Activations Density 0.126%

    No Known Activations