© 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. 48564
    Prev
    Next
    INDEX
    Explanations

    breeding, nesting, colonies, success

    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
    ä¼ļè®©ä½ł
    -0.09
     complexion
    -0.09
    éĺį
    -0.08
    Marc
    -0.08
    讼
    -0.08
    ç´¯äºĨ
    -0.08
    æĪ¾
    -0.08
    mah
    -0.08
     mah
    -0.08
    éĢ®
    -0.08
    POSITIVE LOGITS
    å¿łå®ŀ
    0.11
    ä¸Ģ对
    0.10
    åıĮåıĮ
    0.10
    ÑĢÑĥÑĤ
    0.10
    agli
    0.10
    ä¿
    0.10
    æļijæľŁ
    0.10
    stra
    0.09
    家åºŃ
    0.09
    (ERR
    0.09
    Activations Density 0.065%

    No Known Activations