© 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. 2941
    Prev
    Next
    INDEX
    Explanations

    disciplinary measures

    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¯ķ
    -0.09
    æ·«
    -0.09
    æ½ľ
    -0.09
     Mik
    -0.08
    antry
    -0.08
    主é¢ĺ
    -0.08
    è´Ŀ
    -0.08
    å°±æĺ¯åľ¨
    -0.08
    æĢĢæĬ±
    -0.08
    身躯
    -0.08
    POSITIVE LOGITS
    追究
    0.13
    缸åºĶçļĦ
    0.11
    æ³ķå¾ĭ责任
    0.10
    éĢĤå½ĵçļĦ
    0.10
    严èĤĥ
    0.09
    uce
    0.08
    æ±°
    0.08
    ä¹ĥèĩ³
    0.08
    æīĢå¾Ĺ
    0.08
    ipro
    0.08
    Activations Density 0.056%

    No Known Activations