© 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. 52087
    Prev
    Next
    INDEX
    Explanations

    cannot or can

    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
    omap
    -0.11
    itur
    -0.09
    ç«Ł
    -0.09
    ä¸įå®ļ
    -0.09
    kil
    -0.09
    æ®Ĭ
    -0.09
    å¥ĩå¼Ĥ
    -0.09
    ä¿ĿçķĻ
    -0.09
    ä¸įåħį
    -0.08
    ä¸įæŃ¢
    -0.08
    POSITIVE LOGITS
    æ·«
    0.10
    ç»Ŀ对ä¸įä¼ļ
    0.10
    åģ·
    0.10
    루
    0.09
    篡
    0.09
    诳
    0.09
    侵害
    0.09
    ä¸ĵåĮº
    0.09
    ä¸įä¼ļ
    0.09
    çĬ¯
    0.08
    Activations Density 0.144%

    No Known Activations