© 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. 19854
    Prev
    Next
    INDEX
    Explanations

    administrative districts or municipalities

    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
    è¦ļ
    -0.10
    祯
    -0.09
    çľģæķĻèĤ²åİħ
    -0.09
    åı°é£İ
    -0.09
    è´¿
    -0.09
    æĢ»å±Ģ
    -0.09
    ä¹ħ
    -0.09
    imbus
    -0.08
    èĮµ
    -0.08
     дÑĥÑħ
    -0.08
    POSITIVE LOGITS
    åĨħçļĦ
    0.10
    级
    0.09
    éĩĮçļĦ
    0.09
    å§Ķç»Ħç»ĩéĥ¨
    0.09
    pecific
    0.09
    乡éķĩ
    0.09
    ATO
    0.09
    -level
    0.08
    ships
    0.08
    æĿijéĩĮ
    0.08
    Activations Density 0.204%

    No Known Activations