© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 50207
    Prev
    Next
    INDEX
    Explanations

    historical and medical terms

    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
    èĹ»
    -0.09
    uder
    -0.08
    è·¸
    -0.08
    OST
    -0.08
    avar
    -0.08
     Judicial
    -0.08
    æīĢèĥ½
    -0.08
    ixel
    -0.08
    滥
    -0.08
    ç¼ģ
    -0.08
    POSITIVE LOGITS
    ä¼łç»Ł
    0.10
    快讯
    0.09
     enumerable
    0.09
    èĪ¬çļĦ
    0.09
    enant
    0.09
    æ°Ļ
    0.09
    åı¤èĢģ
    0.09
    ÑįÑĦÑĦ
    0.09
    åİĨåı²æĤłä¹ħ
    0.08
    å¾Īæ¸ħæ¥ļ
    0.08
    Activations Density 0.389%

    No Known Activations