© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52253
    Prev
    Next
    INDEX
    Explanations

    employment intermediary

    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
    纵
    -0.10
     grandchildren
    -0.09
    çŃ¹
    -0.09
    éĩİå¿ĥ
    -0.09
    iro
    -0.09
    篡
    -0.09
     Iz
    -0.09
    åĢ¼å¾Ĺä¸Ģ
    -0.09
    è§Ĭ
    -0.09
    vale
    -0.09
    POSITIVE LOGITS
    åĬ³åĬ¨èĢħ
    0.13
    çĶ¨å·¥
    0.12
    éĽĩ主
    0.11
    åĬ³åĬ¨
    0.11
    åĥįãģį
    0.10
    åĬ³åĬ¨åIJĪåIJĮ
    0.10
    åģļå·¥
    0.10
     Workers
    0.10
    ä¸įå®ļ
    0.10
    å·¥ä½ľçļĦ
    0.10
    Activations Density 0.146%

    No Known Activations