© 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. 51109
    Prev
    Next
    INDEX
    Explanations

    economic development finance

    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
    笳
    -0.12
    认
    -0.12
    çªĪ
    -0.11
     полÑĥÑĩа
    -0.11
    æĪ¾
    -0.11
    èµ·éĩįæľº
    -0.10
    åıĹ访
    -0.10
    è¿Ŀæ³ķçĬ¯ç½ª
    -0.10
    åIJ©
    -0.10
    vi
    -0.10
    POSITIVE LOGITS
    æĪ¿åŃIJ
    0.08
    èĨı
    0.07
    noc
    0.07
     Tate
    0.07
     deduct
    0.07
     defs
    0.07
    ä¸ĢåĪ»
    0.07
    gart
    0.07
    agen
    0.07
     crown
    0.07
    Activations Density 0.017%

    No Known Activations