© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21258
    Prev
    Next
    INDEX
    Explanations

    in [location/time/state]

    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
    éĺħ
    -0.09
    麻
    -0.09
    successful
    -0.08
    ä¸Ĭ次
    -0.08
    æµ·æ¹¾
    -0.08
    æİĪä¿¡
    -0.08
    ror
    -0.08
    工夫
    -0.08
    ãģªãģĭ
    -0.08
    ç«ĭéĿ¢
    -0.08
    POSITIVE LOGITS
    åIJĦ个æĸ¹éĿ¢
    0.11
    æľĢéĢĤåIJĪ
    0.09
    åIJĦ级
    0.09
    ä¸įåIJĮç¨ĭ度
    0.08
    äºĨä¸Ģ个
    0.08
    ä¸ĥ个
    0.08
    éĥ½åĸľæ¬¢
    0.08
    ä¸Ģé¢Ĺ
    0.08
    orsk
    0.08
    æľĢå¤ļçļĦ
    0.08
    Activations Density 0.113%

    No Known Activations