© 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. 20922
    Prev
    Next
    INDEX
    Explanations

    Jets and Rays baseball teams

    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
    zelf
    -0.10
    kdir
    -0.09
    arta
    -0.09
    ity
    -0.09
    èµ·æĿ¥
    -0.09
    ç¥Ģ
    -0.09
    гÑĥ
    -0.08
    æ¸ł
    -0.08
    vil
    -0.08
    erialize
    -0.08
    POSITIVE LOGITS
    ëįķ
    0.09
    é¬ĵ
    0.09
    foil
    0.09
    纶
    0.09
    ted
    0.09
    à¹Ĥà¸Ľà¸£à¸Ķ
    0.09
    èĬ¦
    0.08
    duino
    0.08
    phony
    0.08
    anja
    0.08
    Activations Density 0.007%

    No Known Activations