© 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. 26764
    Prev
    Next
    INDEX
    Explanations

    possessive or 'has' followed by verb/noun

    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
    ä¸Ńåħ±
    -0.11
    åī§ç»Ħ
    -0.11
    ãģ»ãģĨ
    -0.10
    æīĢåľ¨
    -0.10
    ç»Ħå§Ķä¼ļ
    -0.10
    ä¸ŃåĽ½éĺŁ
    -0.10
    åĮºæĶ¿åºľ
    -0.09
    ende
    -0.09
    æĹ¶ä»£ä¸ŃåĽ½
    -0.09
    ä¸Ĭæĸ¹
    -0.09
    POSITIVE LOGITS
    æݨåĩºçļĦ
    0.13
    ç»ĻæĪij们
    0.10
    æݨåĩº
    0.10
    æݨåĩºäºĨ
    0.10
     пÑĢодÑĥк
    0.09
    åĶ®
    0.08
    å¤įæ´»
    0.08
    ç§ijåѦæĬĢæľ¯
    0.08
    Bang
    0.08
     product
    0.08
    Activations Density 0.149%

    No Known Activations