© 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. 35186
    Prev
    Next
    INDEX
    Explanations

    Shinzo, Shinji, shin splints

    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
    инÑĭ
    -0.11
    æłĸ
    -0.10
    åĴĮåľ°åĮº
    -0.10
    ä½Ĩä¸įéĻIJäºİ
    -0.09
    ä¸įå°½
    -0.09
    ëģĶ
    -0.09
     Kut
    -0.09
    大åħ¨
    -0.09
    æł·çļĦ
    -0.09
    èļĬ
    -0.09
    POSITIVE LOGITS
    lish
    0.11
    лÑij
    0.10
    ../
    0.09
    tet
    0.08
    DIRECT
    0.08
    burn
    0.08
    èĬ½
    0.08
     guar
    0.08
     Coco
    0.08
    ä¸įæķ¢
    0.08
    Activations Density 0.011%

    No Known Activations