© 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. 11528
    Prev
    Next
    INDEX
    Explanations

    over a duration or quantity

    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
     ResourceType
    -0.09
    æĸ¹éĿ¢çļĦ
    -0.09
     Kah
    -0.08
    ting
    -0.08
    éĻ¤éĿŀ
    -0.08
    ering
    -0.08
     Shir
    -0.08
    bing
    -0.08
    ((&
    -0.08
    rees
    -0.08
    POSITIVE LOGITS
    éķ¿æľŁä»¥æĿ¥
    0.10
    ä¿İ
    0.10
    åĴİ
    0.09
    å¤ļå¹´æĿ¥
    0.09
    å«Į
    0.09
    è¿Ļä¹Īå¤ļå¹´
    0.09
    æĺ¯ä¸ª
    0.09
    ERY
    0.09
    è¿Ļåĩłå¹´
    0.09
     Soup
    0.08
    Activations Density 0.022%

    No Known Activations