© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 26626
    Prev
    Next
    INDEX
    Explanations

    precision magnification microscopy

    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
    nemonic
    -0.09
    ä¼Ļ
    -0.09
    eton
    -0.08
     Alam
    -0.08
    è¸Ĭè·ĥ
    -0.08
    æį©
    -0.08
    æĮ¥æīĭ
    -0.08
    æ´§
    -0.08
    '](
    -0.08
    秦çļĩ
    -0.08
    POSITIVE LOGITS
    ç²¾ç»Ĩ
    0.13
    ç²¾å¯Ĩ
    0.13
    ç»Ĩèĩ´
    0.13
    ç²¾æ¹Ľ
    0.12
    纤
    0.12
    ç²¾ç»ĨåĮĸ
    0.12
    å¾®åŀĭ
    0.11
    精确
    0.11
    精度
    0.11
    å°ıå¿ĥ
    0.11
    Activations Density 0.205%

    No Known Activations