© 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. 52892
    Prev
    Next
    INDEX
    Explanations

    multilingual education, school names

    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
    èıĩ
    -0.10
     cord
    -0.10
    æŁŀ
    -0.09
    cord
    -0.09
    æ·¹
    -0.08
    ãĤ®ãĥ£
    -0.08
    lean
    -0.08
    寡
    -0.08
     compression
    -0.08
    ä¸įç®Ĺ
    -0.08
    POSITIVE LOGITS
    让åŃ©åŃIJ
    0.14
    åŃ©åŃIJçļĦ
    0.13
    家éķ¿
    0.12
    è¡ĹåĮº
    0.12
    åŃ©åŃIJ
    0.12
     District
    0.11
    çļĦåŃ©åŃIJ
    0.11
     child
    0.10
     district
    0.10
     niño
    0.10
    Activations Density 0.036%

    No Known Activations