© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 50889
    Prev
    Next
    INDEX
    Explanations

    eating, meals, and dining

    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
    æł¹æį®ä¸įåIJĮ
    -0.09
    çĶŁæ´»åľ¨
    -0.09
     baking
    -0.09
    ç»ĥ
    -0.09
    ÑĥÑīе
    -0.09
     Bake
    -0.09
    æŁľ
    -0.09
    çĥĺçĦĻ
    -0.09
    lingen
    -0.08
    responseObject
    -0.08
    POSITIVE LOGITS
    çŃ·åŃIJ
    0.14
    çĶ¨æīĭ
    0.11
     fork
    0.11
    çŃ·
    0.10
    åIJĥå®Į
    0.10
    æ¡Įä¸Ĭ
    0.10
    é¤IJåħ·
    0.10
    åķľ
    0.10
    åıī
    0.10
    æľįåĬ¡åijĺ
    0.10
    Activations Density 0.047%

    No Known Activations