© 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. 36708
    Prev
    Next
    INDEX
    Explanations

    point where

    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
    è¯
    -0.09
    å¾Ļ
    -0.09
    æ¼¾
    -0.09
    è°ĥæŁ¥æĺ¾ç¤º
    -0.08
    æī«ä¸Ģæī«
    -0.08
    çľĭéĩį
    -0.08
    kar
    -0.08
    SIZE
    -0.08
    å¿ĥä¸ŃçļĦ
    -0.08
    åĮ¡
    -0.08
    POSITIVE LOGITS
    çļĦåľ°æŃ¥
    0.16
    åĪ°äºĨ
    0.16
    以èĩ³äºİ
    0.15
    çļĦç¨ĭ度
    0.14
    ç¨ĭ度
    0.14
    è¾¾åĪ°äºĨ
    0.14
     ÑĥÑĢовнÑı
    0.14
    å¢ĥçķĮ
    0.13
     level
    0.13
    è¾¾åĪ°
    0.13
    Activations Density 0.087%

    No Known Activations