© 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. 26799
    Prev
    Next
    INDEX
    Explanations

    defy odds, tradition, and expectations

    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
    åºĶ对
    -0.10
    ÙģÙĤ
    -0.09
     Gone
    -0.09
    Absolutely
    -0.09
    uffers
    -0.09
    ä¸įåı¯ç¼ºå°ij
    -0.09
    黯
    -0.09
    ç
    -0.09
    æľįåĬ¡å¹³åı°
    -0.09
    ä¼´éļıçĿĢ
    -0.09
    POSITIVE LOGITS
    å·²ä¹ħ
    0.10
    ä¼łç»Ł
    0.09
     convention
    0.09
    ingly
    0.09
     веÑģÑĮ
    0.08
    æĢ»ä½ĵè§ĦåĪĴ
    0.08
    æ½®æµģ
    0.08
     circumstance
    0.08
    è®°èĢħäºĨ解
    0.08
     tradition
    0.08
    Activations Density 0.014%

    No Known Activations