© 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. 37302
    Prev
    Next
    INDEX
    Explanations

    as far as

    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
    ANTI
    -0.09
    大大æıIJé«ĺ
    -0.09
    æ¶Ł
    -0.09
    æĢİ
    -0.09
    åı¯ä»¥æĽ´å¥½
    -0.09
    åĹĦ
    -0.09
    æ¯ĽåŃĶ
    -0.08
    æ§ģ
    -0.08
    .slides
    -0.08
    POSITIVE LOGITS
    èĢĮè¨Ģ
    0.19
    æĿ¥è¯´
    0.17
    æĿ¥è®²
    0.16
    çļĦ人æĿ¥è¯´
    0.14
    ä¾Ĩ說
    0.13
    çݩ家æĿ¥è¯´
    0.11
    æĸ¹éĿ¢
    0.11
    æĪĺ士æĿ¥è¯´
    0.10
    è¿Ļæĸ¹éĿ¢
    0.10
     regarding
    0.10
    Activations Density 0.024%

    No Known Activations