© 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. 63029
    Prev
    Next
    INDEX
    Explanations

    SQL connection

    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
    ä¹Łæľīå¾Īå¤ļ
    -0.10
    nex
    -0.10
    æķ£
    -0.09
    笫
    -0.09
    è¿Ļ两ç§į
    -0.09
    uez
    -0.09
    æĽ³
    -0.09
    ÙģÙĪ
    -0.09
    è²Į
    -0.08
    ä¸įåľ¨
    -0.08
    POSITIVE LOGITS
    è¿Ļåı¥è¯Ŀ
    0.13
    è¿Ļè¯Ŀ
    0.10
    èŁł
    0.09
    ä¹Łå°±æĺ¯è¯´
    0.09
    åĵī
    0.08
    æĢ»ä¹¦è®°
    0.08
    æį¢åı¥è¯Ŀ说
    0.08
    sic
    0.08
    è¿Ļæł·çļĦè¯Ŀ
    0.08
    è¿Ļå°±
    0.08
    Activations Density 0.216%

    No Known Activations