© 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. 2070
    Prev
    Next
    INDEX
    Explanations

    special meeting or session

    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
    弯
    -0.09
    avl
    -0.09
     xếp
    -0.09
    è¾Ķ
    -0.09
    ä¸ĢåĢĭ人
    -0.09
     ÑĢоман
    -0.09
    ä¸Ģ个人
    -0.09
    è¿Ľåĩºåı£
    -0.09
    é»ĺé»ĺ
    -0.09
    aille
    -0.09
    POSITIVE LOGITS
    åı¬å¼Ģ
    0.14
    åı¬
    0.10
     meetings
    0.10
    ä¼ļè®®
    0.10
     meeting
    0.10
    举è¡Į
    0.10
    å¼Ģä¼ļ
    0.10
    meeting
    0.09
    æĪIJç«ĭ
    0.09
    大ä¼ļ
    0.09
    Activations Density 0.084%

    No Known Activations