© 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. 18256
    Prev
    Next
    INDEX
    Explanations

    law and regulations

    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
    æķĽ
    -0.08
    éķ£
    -0.08
    esc
    -0.08
    ä»Ģä¹Īéĥ½
    -0.08
    ç»İ
    -0.07
     derivation
    -0.07
    elin
    -0.07
    ä¸ĢåĪĩéĥ½æĺ¯
    -0.07
    度è¿ĩ
    -0.07
     qint
    -0.07
    POSITIVE LOGITS
    类似çļĦ
    0.10
    åľ¨è¿Ļæĸ¹éĿ¢
    0.09
    åºĸ
    0.09
    æĿĸ
    0.09
    çłĶ究表æĺİ
    0.09
    åIJĮç±»
    0.09
    çĮĹ
    0.09
    oters
    0.09
    æłĩåĩĨåĮĸ
    0.09
    æŃ¤ä¸¾
    0.09
    Activations Density 0.550%

    No Known Activations