© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 57251
    Prev
    Next
    INDEX
    Explanations

    hourly workers and overtime

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ÑħоÑĤÑĮ
    -0.08
    åįĬ个
    -0.08
     Sap
    -0.08
    _tac
    -0.08
     bó
    -0.08
    atics
    -0.07
    æģĴ
    -0.07
    åį·
    -0.07
    æľ¬è´¨
    -0.07
    sWith
    -0.07
    POSITIVE LOGITS
    ä»İä¸Ń
    0.10
    ape
    0.09
    éĤĿ
    0.09
    èĥª
    0.09
     concess
    0.09
    ä½łçİ°åľ¨
    0.09
    pur
    0.09
    éĥ¨ä¸»ä»»
    0.09
    .addObject
    0.09
    upy
    0.09
    Activations Density 0.006%

    No Known Activations