© 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. 5741
    Prev
    Next
    INDEX
    Explanations

    gaining benefits and recognition

    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
    eid
    -0.09
     helm
    -0.09
    æݪæĸ½
    -0.08
    éĽĨåIJĪ
    -0.08
     unanimous
    -0.08
    hart
    -0.08
    éļ¶å±ŀäºİ
    -0.08
    cho
    -0.08
    羣åģĩ
    -0.08
    lem
    -0.08
    POSITIVE LOGITS
    èĩªèº«çļĦ
    0.12
    éªł
    0.12
    ä¸įçķĻ
    0.12
    ç£ķ
    0.11
    äºĨèĩªå·±çļĦ
    0.11
    æľ¬èº«çļĦ
    0.10
    ç»ıè´¸
    0.10
    èĩªèº«
    0.10
    æīĭ表
    0.10
     Watch
    0.09
    Activations Density 0.069%

    No Known Activations