© 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. 11391
    Prev
    Next
    INDEX
    Explanations

    counting, including, excluding

    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
    æĪĸå¤ļ
    -0.10
    оÑī
    -0.10
    æĿŁ
    -0.10
    .qt
    -0.10
    ä¾ĽçĶµåħ¬åı¸
    -0.10
    èĪħ
    -0.09
    åħ±åIJĮä½ĵ
    -0.09
    dzi
    -0.09
    ä¸Ńç§ĭèĬĤ
    -0.09
    ç»ıèIJ¥æ¨¡å¼ı
    -0.09
    POSITIVE LOGITS
    ä¸įç®Ĺ
    0.13
     counting
    0.12
     counted
    0.10
    æľīå¤ļå°ij
    0.10
     Count
    0.10
     ká»ĥ
    0.09
    纳åħ¥
    0.09
     counts
    0.09
    ä¹Łç®Ĺ
    0.09
    è¿ĽæĿ¥
    0.09
    Activations Density 0.062%

    No Known Activations