© 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. 62833
    Prev
    Next
    INDEX
    Explanations

    degrees C or hours

    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
    ç´Ģ
    -0.10
    åįĥéĩĮ
    -0.09
    åĻ
    -0.08
    æ°¸è¿ľä¸įä¼ļ
    -0.08
    _MALLOC
    -0.08
    æĽ´å¤ļçļĦæĺ¯
    -0.08
    æĹłåĬ©
    -0.08
     perennial
    -0.08
    纪
    -0.07
    æľĢæĹ©
    -0.07
    POSITIVE LOGITS
    ards
    0.10
     vÃłi
    0.09
    çIJĨ解åĴĮ
    0.09
    åĽĽäºĶ
    0.09
    ä¼ģä¸ļåĴĮ
    0.09
    лог
    0.09
     birkaç
    0.09
    неÑģ
    0.08
    å·³
    0.08
    主åħ¬
    0.08
    Activations Density 0.041%

    No Known Activations