© 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. 21275
    Prev
    Next
    INDEX
    Explanations

    rural and urban localities

    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
    ç»ĵ论
    -0.10
    åī©
    -0.10
     junk
    -0.09
    æĭį
    -0.09
     bande
    -0.09
    ETO
    -0.09
    åģ¿
    -0.09
    æĪIJåĵģ
    -0.09
    asy
    -0.08
    åĪĿè¡·
    -0.08
    POSITIVE LOGITS
    åĨľæĿij
    0.13
     rural
    0.12
    乡æĿij
    0.11
     Rural
    0.10
    åĨľè´¸
    0.10
    ä¸Ģä½ĵåĮĸ
    0.10
     countryside
    0.09
    Ñĥв
    0.08
    .remote
    0.08
    çijĻ
    0.08
    Activations Density 0.209%

    No Known Activations