© 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. 11336
    Prev
    Next
    INDEX
    Explanations

    action, imagem, prova

    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
     stesso
    -0.15
     himself
    -0.15
    çļĦ妻åŃIJ
    -0.14
     koji
    -0.13
    inho
    -0.13
     electrónico
    -0.11
    /she
    -0.11
    илÑģÑı
    -0.10
    ÑģÑĤво
    -0.10
    /her
    -0.10
    POSITIVE LOGITS
     herself
    0.19
     italiana
    0.18
     коÑĤоÑĢаÑı
    0.16
     должна
    0.16
     ÙĨÙģسÙĩا
    0.15
     pública
    0.15
     коÑĤоÑĢÑĥÑİ
    0.15
     ÑģÑĤала
    0.14
     бÑĭла
    0.14
    ä¸Ī夫
    0.14
    Activations Density 0.461%

    No Known Activations