© 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. 58696
    Prev
    Next
    INDEX
    Explanations

    descriptive words for places

    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
    åįİ人
    -0.10
    çļĦæľĭåıĭ
    -0.10
    çļĦ强大
    -0.09
    æĺİæĹ¥
    -0.09
    éªĦ
    -0.09
    ä¸Ģåı·
    -0.09
    èĥĨ
    -0.09
    mighty
    -0.09
    è¦ģç´§
    -0.09
    碰åĪ°
    -0.09
    POSITIVE LOGITS
     picturesque
    0.13
    ç«¥è¯Ŀ
    0.13
    浪漫
    0.12
     Romantic
    0.11
    ç¾İçļĦ
    0.11
    åħ¸éĽħ
    0.11
    æ°ĽåĽ´
    0.11
     romantic
    0.11
    ç¾İ好
    0.10
    æĦıå¢ĥ
    0.10
    Activations Density 0.097%

    No Known Activations