© 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. 21547
    Prev
    Next
    INDEX
    Explanations

    other or another followed by media, films, subscription, or images

    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
     обоÑĢ
    -0.10
    allon
    -0.10
    èĮĢ
    -0.09
    ä¹łæĥ¯äºĨ
    -0.09
    管çIJĨåĴĮ
    -0.09
    Ä°N
    -0.08
    çŁ¥è¯ĨçĤ¹
    -0.08
    atoon
    -0.08
     Elk
    -0.08
    å·¥ç¨ĭè´¨éĩı
    -0.08
    POSITIVE LOGITS
    ç°§
    0.11
    æĬ¼ãģĹ
    0.09
     Harding
    0.08
    åľ¨åIJĮä¸Ģ
    0.08
    æĶ¯è¡Į
    0.08
    çļĦæĪ¿åŃIJ
    0.08
    æĽ´æľī
    0.08
     ׼׼×Ķ
    0.08
    åĽºçĦ¶
    0.08
    æIJı
    0.08
    Activations Density 0.032%

    No Known Activations