© 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. 22729
    Prev
    Next
    INDEX
    Explanations

    nuclear fuel, cargo ship, insulation, spent nuclear fuel

    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
    ç½®ä¸ļ
    -0.11
    æºĥ
    -0.10
    æĸ°è¥¿
    -0.10
    ustr
    -0.09
    çĻ£
    -0.09
    è·Łä¸įä¸Ĭ
    -0.09
    èĩªçĦ¶èĢĮçĦ¶
    -0.09
    奢
    -0.09
    è£ĺ
    -0.09
    æĮij
    -0.08
    POSITIVE LOGITS
    olumn
    0.09
    人æĢ§
    0.09
    èµ·éĩįæľº
    0.09
    颧
    0.08
    orado
    0.08
    çĩķ
    0.08
    주ìĿĺ
    0.08
     liá»ĩt
    0.08
     Units
    0.08
     Haven
    0.08
    Activations Density 0.097%

    No Known Activations