© 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. 22317
    Prev
    Next
    INDEX
    Explanations

    urgical strategies

    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
    æ´¾
    -0.11
    æī¿æİ¥
    -0.10
    派人
    -0.09
    è¯ŀ
    -0.08
    大éĻĨ
    -0.08
    è¿Ľé©»
    -0.08
    ä¸ºæľŁ
    -0.08
    åĽłä¸ºä½ł
    -0.08
    ä¸Ģåı·
    -0.08
    çīĮ
    -0.08
    POSITIVE LOGITS
    éİĸ
    0.09
    ë³ij
    0.09
    illet
    0.08
    زÙĦ
    0.08
    缶
    0.08
    åħĪåIJİ
    0.08
    ç»ı纪
    0.08
    asl
    0.08
    çľ¼ä¸ĭ
    0.08
    émon
    0.08
    Activations Density 0.017%

    No Known Activations