© 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. 17418
    Prev
    Next
    INDEX
    Explanations

    my/our noun

    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
    åĬ¡
    -0.10
    è¿ĻäºĽä¸ľè¥¿
    -0.09
    ä¼ĺç§Ģ
    -0.09
    .Rollback
    -0.09
    快讯
    -0.09
    æ¿ij
    -0.09
    åīĭ
    -0.08
    åľ¨è¿Ļæĸ¹éĿ¢
    -0.08
    _Framework
    -0.08
    mgr
    -0.08
    POSITIVE LOGITS
    éĤ£æ¬¡
    0.12
    æ¯ıä¸Ģ次
    0.11
    è¿Ļåľº
    0.11
    ä¾ĭè¡Į
    0.10
    讨论
    0.10
    çªģå¦Ĥåħ¶
    0.09
     discussions
    0.09
    æī¶è´«å·¥ä½ľ
    0.09
    è¡Įç¨ĭ
    0.09
    è°Īè¯Ŀ
    0.09
    Activations Density 0.623%

    No Known Activations