© 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. 36748
    Prev
    Next
    INDEX
    Explanations

    locations following "of" or "downtown"

    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
    æĸ½
    -0.10
    éķ¿éĢĶ
    -0.09
    æµĻæ±Ł
    -0.09
    åĨĴ
    -0.09
    è··
    -0.09
    æĹħéĢĶ
    -0.09
    éķ¿æ±Ł
    -0.09
    æ±Łèĭı
    -0.09
     æĸ
    -0.08
    éĤ£åĦ¿
    -0.08
    POSITIVE LOGITS
    主åŁİåĮº
    0.19
    å¸Ĥä¸Ńå¿ĥ
    0.17
    åŁİåĮº
    0.17
    å¸ĤåĮº
    0.17
     downtown
    0.16
     urban
    0.16
    è¿ĽåŁİ
    0.16
    åŁİéĩĮ
    0.16
    åŁİå¸Ĥ
    0.15
    ä¸Ńå¿ĥåŁİåĮº
    0.15
    Activations Density 0.165%

    No Known Activations