© 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. 20104
    Prev
    Next
    INDEX
    Explanations

    life, property, environment

    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
    ä¹±
    -0.09
    éģ¿
    -0.09
    mani
    -0.08
    æĭ¿äºĨ
    -0.08
    æĿĤ
    -0.08
    æīĵ交éģĵ
    -0.08
    帮æī¶
    -0.08
    æIJŀå®ļ
    -0.08
    è·³åĩº
    -0.08
    乱象
    -0.08
    POSITIVE LOGITS
    æľīçļĦçݩ家
    0.10
     внÑĥÑĤÑĢи
    0.09
    游æĪıåī¯æľ¬
    0.08
    ä¸įæĸŃå¢ŀ强
    0.08
    ált
    0.08
    eyer
    0.08
    æĸ°åŀĭåĨł
    0.08
    æļ
    0.08
    æĸ°åŀĭåĨłçĬ¶
    0.08
    åĬª
    0.08
    Activations Density 0.233%

    No Known Activations