© 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. 21406
    Prev
    Next
    INDEX
    Explanations

    authors, scholars, investigators, analysts

    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
    她说
    -0.09
    éķ¿çº¦
    -0.09
    дов
    -0.08
    éĹ®éĹ®
    -0.08
    干活
    -0.08
     اÙĦض
    -0.08
    _alias
    -0.08
    éļ¨æĻĤ
    -0.08
    awaiter
    -0.08
    饶
    -0.08
    POSITIVE LOGITS
    æĬĬè¿Ļ个
    0.10
    åѦèĢħ
    0.10
    ovah
    0.09
    åŃľ
    0.09
    åģļè¿ĩ
    0.09
    åĨĻåĩº
    0.09
    çIJ¦
    0.09
     иÑģÑģлед
    0.09
    ç»ĻäºĨæĪij
    0.09
    æ¥ŀ
    0.08
    Activations Density 0.130%

    No Known Activations