© 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. 60138
    Prev
    Next
    INDEX
    Explanations

    dictatorship, regime, military rule, civil war

    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
     mex
    -0.07
     Bronx
    -0.07
     mexicana
    -0.06
    Mex
    -0.06
    éĩį大éģĹæ¼ı
    -0.06
    umps
    -0.06
     addition
    -0.06
     Grec
    -0.06
     Wien
    -0.06
     Syrie
    -0.06
    POSITIVE LOGITS
     restructuring
    0.09
     elites
    0.09
     regime
    0.08
    éŃ
    0.08
    -lite
    0.08
    æĶ¿å±Ģ
    0.08
     Parch
    0.08
     Reconstruction
    0.08
     nationalist
    0.08
     конÑģÑĤиÑĤÑĥ
    0.08
    Activations Density 0.647%

    No Known Activations