© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36308
    Prev
    Next
    INDEX
    Explanations

    seemingly, apparently, day, plus

    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
    解æĶ¾æĢĿæĥ³
    -0.10
    æ¿ĢåĬ¨
    -0.09
    æĸ°é¢ĸ
    -0.09
    轶
    -0.09
    ä¼łè¾¾
    -0.09
    ä¸į失
    -0.08
    åĢ¼å¾Ĺä¸Ģ
    -0.08
    å¥ĭè¿Ľ
    -0.08
    éĩįä¸Ń
    -0.08
    çľ¼è§Ĵ
    -0.08
    POSITIVE LOGITS
    åĩĨåħ¥
    0.10
    ä¾Ľç»Ļ侧
    0.09
    æĬµ
    0.08
    ç¨Ģ
    0.08
    èĦĨå¼±
    0.08
    è´Ńç½®
    0.07
    ĤŃ
    0.07
     relative
    0.07
     Rousse
    0.07
    é«ĺé¢Ŀ
    0.07
    Activations Density 0.263%

    No Known Activations