© 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. 9347
    Prev
    Next
    INDEX
    Explanations

    engine or vehicle part

    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
    åĨĴ
    -0.10
    ypsum
    -0.10
     обÑĬÑıвл
    -0.09
     игÑĢовÑĭе
    -0.09
    ç¼¥
    -0.08
    æĨ¨
    -0.08
    ouflage
    -0.08
    NIL
    -0.08
     NIL
    -0.08
    å¿ĥä¸Ń
    -0.08
    POSITIVE LOGITS
    æľĢæĸ°çļĦ
    0.12
    åIJĮæł·çļĦ
    0.12
    ä¸Ģæł·çļĦ
    0.10
    è¿Ļå¥Ĺ
    0.10
    åħ¨å¥Ĺ
    0.10
    缸åIJĮçļĦ
    0.10
    æľĢåħĪè¿ĽçļĦ
    0.09
    ä»Ģä¹Īæł·çļĦ
    0.09
    æIJŃéħį
    0.08
    éĩĩçĶ¨äºĨ
    0.08
    Activations Density 0.119%

    No Known Activations