© 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. 48493
    Prev
    Next
    INDEX
    Explanations

    superlative adverbs and nouns

    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
    æľ¬èº«çļĦ
    -0.09
     пÑĢеж
    -0.09
    делÑĮ
    -0.09
    åºĹéĩĮ
    -0.09
    æµģåĩº
    -0.09
    å½ĵåľ°çļĦ
    -0.09
    æ·Ĩ
    -0.09
    æijĦ
    -0.08
     ÙĨÙģسÙĩا
    -0.08
    åĩ¡äºĭ
    -0.08
    POSITIVE LOGITS
    ä¸įå¤ļ
    0.09
    ake
    0.09
    loth
    0.09
    æľĢæľī
    0.09
    åĶ¯ä¸Ģ
    0.08
     richest
    0.08
    æľĢé«ĺçļĦ
    0.08
    æľĢ大çļĦ
    0.08
    åİŁæĸĩåľ°åĿĢ
    0.08
     largest
    0.08
    Activations Density 0.042%

    No Known Activations