© 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. 22016
    Prev
    Next
    INDEX
    Explanations

    meet standards

    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
    ock
    -0.09
    AspNet
    -0.09
    ä¼Ĭæĭī
    -0.09
     Evel
    -0.09
    éĶĪ
    -0.09
    æ´»åĬ¨çİ°åľº
    -0.09
    ynamic
    -0.09
    è·¨çķĮ
    -0.08
    èįĥ
    -0.08
    è¿Ļ件
    -0.08
    POSITIVE LOGITS
     standards
    0.13
    æłĩåĩĨ
    0.12
    çļĦæłĩåĩĨ
    0.11
     standard
    0.10
    åĽ½å®¶æłĩåĩĨ
    0.10
     specs
    0.10
     ÑĤÑĢебованиÑı
    0.09
    ä¸ļ
    0.09
    æ¨Ļæºĸ
    0.09
     industry
    0.09
    Activations Density 0.053%

    No Known Activations