© 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. 22385
    Prev
    Next
    INDEX
    Explanations

    school grades K-12

    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
    åŁİå¸Ĥåıijå±ķ
    -0.10
    avs
    -0.09
     laz
    -0.08
    ç«ŀæĬĢ
    -0.08
    æį®
    -0.08
    orias
    -0.08
    unt
    -0.08
    æ¸ħè¿ľ
    -0.08
    æıŃæĻĵ
    -0.08
     deeply
    -0.08
    POSITIVE LOGITS
    å°ıåѦ
    0.16
     school
    0.14
    å°ıåѦçĶŁ
    0.13
    åĪĿä¸Ń
    0.13
    åŃ¦æł¡
    0.12
    -school
    0.12
    å¹¼åĦ¿åĽŃ
    0.12
     grade
    0.12
    ä¸ŃåѦ
    0.12
    é«ĺä¸ŃçĶŁ
    0.12
    Activations Density 0.086%

    No Known Activations