© 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. 38980
    Prev
    Next
    INDEX
    Explanations

    reluctant or unwilling disposition

    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
    ä¸ģ
    -0.10
    ä¸įçIJĨ
    -0.10
    çŀİ
    -0.09
    æµļ
    -0.09
    ronic
    -0.09
    lify
    -0.09
    æĸ°å½¢åĬ¿
    -0.09
     sic
    -0.09
    orial
    -0.09
    åŀĤ
    -0.08
    POSITIVE LOGITS
    ãģªãģĮãĤī
    0.09
    æģķ
    0.09
    accept
    0.09
     reluctantly
    0.09
    лим
    0.09
    ãģĮãĤī
    0.09
    est
    0.09
    ably
    0.09
    被åĬ¨
    0.09
    éķĴ
    0.09
    Activations Density 0.145%

    No Known Activations