© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51373
    Prev
    Next
    INDEX
    Explanations

    property sales and buying

    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
    aley
    -0.09
    æĺİçĻ½
    -0.09
    quete
    -0.09
    çĽ´è¾¾
    -0.08
    quals
    -0.08
    æľīä¸Ģç§į
    -0.08
    à½Ħ
    -0.08
    ((__
    -0.08
     sắp
    -0.08
    çľĭä¸Ģçľĭ
    -0.08
    POSITIVE LOGITS
    æĪIJ交
    0.14
     happ
    0.10
    éĢĨåĬ¿
    0.09
    该éĻ¢
    0.09
    æĪIJåĬŁçļĦ
    0.09
    离åİ»
    0.09
    åıijæĮ¥äºĨ
    0.09
     consolid
    0.08
    è¶ħé«ĺ
    0.08
    ç»ĻäºĨ
    0.08
    Activations Density 0.027%

    No Known Activations