© 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. 32383
    Prev
    Next
    INDEX
    Explanations

    quantities of millions or tons

    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
    没éĴ±
    -0.10
    寸
    -0.10
    ToDevice
    -0.09
    Salary
    -0.09
    ÙĦØ©
    -0.08
     Pai
    -0.08
    à¹Ģà¸ĩ
    -0.08
    ophobic
    -0.08
    åIJĿ
    -0.08
    eld
    -0.08
    POSITIVE LOGITS
    æĢ»éĩı
    0.15
    产éĩı
    0.14
    ä¸ĩåIJ¨
    0.13
    年产
    0.12
    ä¸ĸçķĮ第ä¸Ģ
    0.12
    éĶĢéĩı
    0.11
    ä¾ĽåºĶ
    0.11
    æķ°éĩı
    0.11
     quantities
    0.10
    第äºĮ大
    0.10
    Activations Density 0.058%

    No Known Activations