© 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. 37653
    Prev
    Next
    INDEX
    Explanations

    Facebook account

    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´Ĺæīĭ
    -0.10
    çħ
    -0.10
    à¸ķำ
    -0.09
     ÑĦоÑĢма
    -0.09
    éĤ£åıª
    -0.09
    ä¼łè¾¾
    -0.09
    ä¸ĢéŨ
    -0.08
    athe
    -0.08
    èµ·æĿ¥
    -0.08
    æłĩåĩĨåĮĸ
    -0.08
    POSITIVE LOGITS
    æľį
    0.10
    itters
    0.09
     Vest
    0.09
     pll
    0.09
    amazon
    0.09
    åħ»èĢģæľįåĬ¡
    0.09
    åŃ£
    0.09
    getQuery
    0.08
    GRAM
    0.08
     spun
    0.08
    Activations Density 0.054%

    No Known Activations