© 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. 3443
    Prev
    Next
    INDEX
    Explanations

    abstract paintings and art

    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
    ìĤŃ
    -0.10
    ä¸įæŃ»
    -0.10
     обоÑĢ
    -0.09
    éĽ¢ãĤĮ
    -0.09
    æ¯Ľ
    -0.09
    åĽ¢ç»ĵ
    -0.09
    ä¸įæĥľ
    -0.09
    åĽ¢
    -0.09
    çĬĬ
    -0.08
    à¸Ńà¸ļ
    -0.08
    POSITIVE LOGITS
    åĬŁå¤«
    0.09
    æĶ¹éĿ©å¼ĢæĶ¾
    0.09
    æ´¾
    0.08
    top
    0.08
    Abstract
    0.08
     Eg
    0.08
     Abstract
    0.08
    енной
    0.08
    太平æ´ĭ
    0.08
     sed
    0.08
    Activations Density 0.092%

    No Known Activations