© 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. 19864
    Prev
    Next
    INDEX
    Explanations

    Korean media and names

    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
    åįķåħĥ
    -0.10
    éªij士
    -0.10
    inc
    -0.09
    åĽ´
    -0.09
    BREAK
    -0.09
     никак
    -0.08
    æĦĪ
    -0.08
    incare
    -0.08
    andes
    -0.08
    _SHIFT
    -0.08
    POSITIVE LOGITS
    çļĦç«ŀäºī
    0.10
    èµ°åIJij
    0.10
    æĺ¯éŁ©åĽ½
    0.10
    宣
    0.09
    åħijçİ°
    0.09
    詹
    0.09
     Korean
    0.09
    mons
    0.09
    ä¸įä¿¡
    0.09
    æ
    0.09
    Activations Density 0.087%

    No Known Activations