© 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. 4940
    Prev
    Next
    INDEX
    Explanations

    urban areas and cities

    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
    潺
    -0.10
    fiber
    -0.10
    æĢ§æĦŁ
    -0.10
    elles
    -0.09
    IOR
    -0.09
    æŁģ
    -0.09
    ä¸Ńä»ĭ
    -0.09
     Beds
    -0.09
    è²Į
    -0.09
    çĮ¿
    -0.08
    POSITIVE LOGITS
    éĥ½å¸Ĥ
    0.14
    åŁİå¸Ĥ
    0.12
    è¡Ĺéģĵ
    0.12
     pavement
    0.12
     urban
    0.11
     Urban
    0.10
    人工
    0.10
    Urban
    0.10
    è¡Ĺ头
    0.09
     surface
    0.09
    Activations Density 0.058%

    No Known Activations