© 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. 51098
    Prev
    Next
    INDEX
    Explanations

    universities and colleges

    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
    lige
    -0.09
    รà¸ģ
    -0.08
    _surf
    -0.08
     advert
    -0.08
    .foundation
    -0.08
    åѤç«ĭ
    -0.08
    orgen
    -0.08
    éľĦ
    -0.08
    ODB
    -0.08
     Chap
    -0.08
    POSITIVE LOGITS
    大åѦ
    0.19
    大åѸ
    0.16
     university
    0.15
    å·¥ä¸ļ大åѦ
    0.15
    å¸ĪèĮĥ大åѦ
    0.15
    åĮ»åѦéĻ¢
    0.14
    é«ĺçŃīéĻ¢æł¡
    0.14
    çIJĨ工大åѦ
    0.14
     University
    0.13
     universities
    0.13
    Activations Density 0.133%

    No Known Activations