© 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. 20598
    Prev
    Next
    INDEX
    Explanations

    place names and 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
    nesia
    -0.10
    诲
    -0.10
    ToInt
    -0.10
    æĭ¥æĬ¤
    -0.09
    æĪŁ
    -0.09
    èĩ´çĶµ
    -0.09
    sz
    -0.08
    ìĶ¨
    -0.08
    ä¸įæľį
    -0.08
    ç»ĪçĶŁ
    -0.08
    POSITIVE LOGITS
    容å¿į
    0.10
    -sheet
    0.09
    çĵ¢
    0.09
    èĬ¥
    0.08
    æ³ķ人
    0.08
    alem
    0.08
    黯
    0.08
     bare
    0.08
    quÃŃ
    0.08
    seo
    0.08
    Activations Density 0.010%

    No Known Activations