© 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. 9500
    Prev
    Next
    INDEX
    Explanations

    ensure that / ensure accurate / ensure efficient

    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
    ä½ķå¿ħ
    -0.10
    è¸Ķ
    -0.10
    忽çĦ¶
    -0.10
    oti
    -0.10
    åIJ¦
    -0.10
    æķħæĦı
    -0.09
    ç«ŁçĦ¶
    -0.09
    èĶ¼
    -0.09
    amba
    -0.09
    æĢĢæĬ±
    -0.09
    POSITIVE LOGITS
    ÑĮÑİ
    0.09
    åĪ©çĽĬ
    0.09
    æ£Ģ
    0.09
    ëĮĢë¡ľ
    0.09
    _safe
    0.09
    å®īåħ¨
    0.08
    åIJĦæĸ¹éĿ¢
    0.08
    大家éĥ½åľ¨
    0.08
    жив
    0.08
    éĩįä¸Ń
    0.08
    Activations Density 0.050%

    No Known Activations