© 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. 27557
    Prev
    Next
    INDEX
    Explanations

    do not edit or abuse

    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
    æĿ¥ä¸įåıĬ
    -0.10
    æī¿è®¤
    -0.10
    éķ¶åµĮ
    -0.09
    presso
    -0.09
    çķĻä¸ĭæĿ¥
    -0.09
    å¸®ä½ł
    -0.09
    ç¨įç¨į
    -0.09
    ä¸įæĪIJ
    -0.08
    ä¸Ģè´¯
    -0.08
    æ¯Ķå¦Ĥ说
    -0.08
    POSITIVE LOGITS
    ipa
    0.10
    ç»ĻæĪij
    0.09
    رÙĩ
    0.09
    èİ·å¾ĹæĦŁ
    0.09
     há»ıi
    0.09
    éĹ®æĪij
    0.09
    URY
    0.09
    讶
    0.09
    屡
    0.08
    ç«
    0.08
    Activations Density 0.046%

    No Known Activations