© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36270
    Prev
    Next
    INDEX
    Explanations

    in source and binary forms

    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
    æĺ¾ç¤ºåĩº
    -0.10
     eBooks
    -0.09
    å¾Ĥ
    -0.09
    éĢĬ
    -0.09
    大éģĵ
    -0.08
    ionale
    -0.08
    æ¯ĵ
    -0.08
     Harbor
    -0.08
     Reviewed
    -0.08
    shm
    -0.08
    POSITIVE LOGITS
    éħĿéħ¿
    0.09
    ãģĵãģĿ
    0.09
    活泼
    0.09
     ÑĤоÑĤ
    0.09
    äºĨ大éĩıçļĦ
    0.09
    èĬ
    0.09
    inspace
    0.09
     Burgess
    0.09
    åĨĻäºĨ
    0.09
    åįģå¤ļ
    0.08
    Activations Density 0.011%

    No Known Activations