© 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. 1310
    Prev
    Next
    INDEX
    Explanations

    City Hall, Police Department, Borough Council

    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
    ç²¾åĩĨæī¶è´«
    -0.10
    åħ¨çľģ
    -0.10
    ä¸ī峡
    -0.09
    åı¤åŁİ
    -0.09
    æĹıèĩªæ²»å·ŀ
    -0.09
    orts
    -0.09
     coal
    -0.09
     MSP
    -0.09
    çľģåĨħ
    -0.09
    åĤ¾
    -0.09
    POSITIVE LOGITS
     suburb
    0.09
    æµ·æ·Ģ
    0.09
     suburban
    0.09
    éĥĦ
    0.09
    æ½ľ
    0.09
    éªij
    0.09
    è¤ļ
    0.08
    ensity
    0.08
    é»ĦåŁĶ
    0.08
    å¥łåŁº
    0.08
    Activations Density 0.203%

    No Known Activations