© 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. 37970
    Prev
    Next
    INDEX
    Explanations

    Marx, labour, resources, elections

    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
    çļĦä¿¡
    -0.08
    mö
    -0.08
     Splash
    -0.08
    ä¿¡çļĦ
    -0.08
    uffix
    -0.08
    ä¿¡éģĵ
    -0.08
     تÙĪص
    -0.07
     اÙĦتÙĪص
    -0.07
    åħįè¯ķ
    -0.07
    impa
    -0.07
    POSITIVE LOGITS
    马åħĭæĢĿ
    0.10
    工人çļĦ
    0.10
    åĬ³åĬ¨
    0.09
     labour
    0.09
    工人
    0.09
     Marx
    0.08
     Labour
    0.08
    ä¾Ľæ±Ĥ
    0.08
    çļĦçĶŁäº§
    0.08
    èµĦæľ¬ä¸»ä¹ī
    0.08
    Activations Density 0.001%

    No Known Activations