© 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. 49926
    Prev
    Next
    INDEX
    Explanations

    city and town locations

    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
    çħĬ
    -0.11
    ä¸ĢæŃ¥
    -0.09
    ÑĮе
    -0.09
    bolt
    -0.09
    ä¸Ģ个å¤ļ
    -0.09
    æľīå¤ļ
    -0.08
     окÑĢÑĥжа
    -0.08
    å¤±æľĽ
    -0.08
    è¿ijäºĽ
    -0.08
    é«ij
    -0.08
    POSITIVE LOGITS
    à¸Ĭา
    0.09
    ased
    0.08
    åľ°éľĩ
    0.08
     Keith
    0.08
     ÑģмÑĭÑģл
    0.08
    ç®´
    0.08
    avel
    0.08
    æĢ¥éĢŁ
    0.08
    airy
    0.08
    å¹½
    0.08
    Activations Density 0.002%

    No Known Activations