© 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. 45717
    Prev
    Next
    INDEX
    Explanations

    economic policy and austerity

    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
    æIJĵ
    -0.07
    Destroyed
    -0.07
    åħ¬åı¸èij£äºĭéķ¿
    -0.07
     ìĨĮì¤ijíķľ
    -0.07
    ä½ľåģĩ
    -0.07
     asci
    -0.07
    .desktop
    -0.07
    çŃīåľºæīĢ
    -0.07
    honneur
    -0.06
    สิ
    -0.06
    POSITIVE LOGITS
    æĸ¹éĴĪ
    0.12
     policies
    0.11
    æĸ¹éĩĿ
    0.11
     policy
    0.10
     austerity
    0.10
     unpopular
    0.10
    çļĦæĸ¹éĴĪ
    0.09
    æĸ½æĶ¿
    0.09
     reforms
    0.09
    æĶ¿çŃĸåĴĮ
    0.09
    Activations Density 0.238%

    No Known Activations