© 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. 58238
    Prev
    Next
    INDEX
    Explanations

    any time

    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
    æIJ¶
    -0.09
    iol
    -0.09
    åįĥä¸ĩ
    -0.09
    _heads
    -0.08
     Ped
    -0.08
    yard
    -0.08
    erras
    -0.08
    Lane
    -0.08
    æĬ¢
    -0.08
    ÑģпоÑĢ
    -0.08
    POSITIVE LOGITS
    ariat
    0.09
    åĪ°æľĢåIJİ
    0.09
    ipse
    0.09
    èµ·åĪĿ
    0.09
    åĪļå¼Ģå§ĭ
    0.09
    ä¹Łä¸įåı¯èĥ½
    0.09
    åľ¨æľªæĿ¥
    0.09
    åľ¨ç½ij绾
    0.08
    .Interval
    0.08
    esseract
    0.08
    Activations Density 0.064%

    No Known Activations