© 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. 57531
    Prev
    Next
    INDEX
    Explanations

    forms of "to be" + various descriptors

    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
    å¾Ģå¾Ģ
    -0.11
    æĢµ
    -0.10
    ä¸Ģçľĭ
    -0.10
    PUTE
    -0.09
    å¾Īå¤ļæŶåĢĻ
    -0.09
    å¾Ģå¾Ģæĺ¯
    -0.09
    å¾Ģå¾Ģä¼ļ
    -0.09
    æłı
    -0.09
    æĪijçĽ¸ä¿¡
    -0.09
    OTO
    -0.09
    POSITIVE LOGITS
    è¿Ļå°±æĺ¯
    0.09
    åīį线
    0.09
    æľĢéĢĤåIJĪ
    0.09
    æĭħè´Ł
    0.09
    å°ıä¼Ļ
    0.09
    å°ĨæĿ¥
    0.09
    arf
    0.09
    æľīå¿ħè¦ģ
    0.08
    ä¹Ŀé¾Ļ
    0.08
    ç½ħ
    0.08
    Activations Density 0.097%

    No Known Activations