© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 56966
    Prev
    Next
    INDEX
    Explanations

    school enrollment and growth

    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
    èµ°åĩºåİ»
    -0.10
    è·³åĩº
    -0.10
    aget
    -0.09
    èĽ°
    -0.09
    åģ¶åĥı
    -0.09
    ç´łæĿIJ
    -0.09
    èĢģ头
    -0.09
    ä¿¡ç®±
    -0.09
    asset
    -0.09
    åĴĮ个人
    -0.09
    POSITIVE LOGITS
    就读
    0.11
     enrollment
    0.11
    åħ¨æĹ¥åĪ¶
    0.11
     Enrollment
    0.11
    å°±è¿ij
    0.10
    æĬ¥åIJį
    0.10
     enroll
    0.10
    仲
    0.09
    宽æķŀ
    0.09
     enrol
    0.09
    Activations Density 0.093%

    No Known Activations