© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9136
    Prev
    Next
    INDEX
    Explanations

    fitness and selection theory

    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
    obil
    -0.10
    ä½łåĸľæ¬¢
    -0.10
    ä¸ĢæīĢ
    -0.09
    /bus
    -0.09
    annon
    -0.09
    æĦŁåĬ¨
    -0.08
    读åIJİ
    -0.08
    æ°ijåĬŀ
    -0.08
    çļĦä¹łæĥ¯
    -0.08
    åħ¬åĬŀ
    -0.08
    POSITIVE LOGITS
    社ä¼ļåĮĸ
    0.11
    Fitness
    0.11
     fitness
    0.11
    fitness
    0.10
     Fitness
    0.10
     competition
    0.10
    çĶŁåij½çļĦ
    0.09
    è¾¾å°Ķ
    0.09
    ç«ŀäºīä¼ĺåĬ¿
    0.09
    缱
    0.09
    Activations Density 0.134%

    No Known Activations