© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9973
    Prev
    Next
    INDEX
    Explanations

    province

    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
    èĻı
    -0.11
    çĤľ
    -0.10
    ä»Ģä¹ĪæŶåĢĻ
    -0.10
    оз
    -0.10
    isma
    -0.09
    rott
    -0.09
     Caval
    -0.09
    身ä¸Ĭ
    -0.09
    å¸Ĥåľºä»·æł¼
    -0.09
    æģģ
    -0.08
    POSITIVE LOGITS
    ìĮį
    0.09
     convers
    0.09
    å¸ĥ
    0.08
    angelog
    0.08
    nio
    0.08
     Spy
    0.08
    ossal
    0.08
    ALTH
    0.08
    chemas
    0.08
    rium
    0.08
    Activations Density 0.104%

    No Known Activations