© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36703
    Prev
    Next
    INDEX
    Explanations

    real estate offers and buyer agreements

    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
    orer
    -0.10
    ADVERTISEMENT
    -0.09
    æıIJèµ·
    -0.08
    åįij
    -0.08
    åľ¨å®¶éĩĮ
    -0.08
    kill
    -0.08
    Advance
    -0.08
    çĪ½
    -0.08
     lean
    -0.08
    é²ľ
    -0.08
    POSITIVE LOGITS
    MLS
    0.12
    è´ŃæĪ¿
    0.10
    ä¹°çļĦ
    0.10
     MLS
    0.10
    buyer
    0.10
    æľĭåıĭ们对
    0.10
    è´Ńä¹°
    0.10
    诫
    0.09
    æĪIJ交
    0.09
    åĿĤ
    0.09
    Activations Density 0.095%

    No Known Activations