© 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. 4423
    Prev
    Next
    INDEX
    Explanations

    el numero, do iTunes, el resultado

    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
     herself
    -0.10
     pública
    -0.10
     básica
    -0.10
     ÙĨÙģسÙĩا
    -0.10
    ese
    -0.10
     própria
    -0.10
    ÑģÑĮ
    -0.09
     italiana
    -0.09
    ında
    -0.09
     latina
    -0.09
    POSITIVE LOGITS
    ãĤ¥
    0.11
    /a
    0.11
    zelf
    0.11
    ãģī
    0.11
    ÑĩаÑģ
    0.10
    sWith
    0.10
    swith
    0.10
    ä¸ĩ象
    0.10
    åĴĮåľ°åĮº
    0.10
    orris
    0.09
    Activations Density 0.096%

    No Known Activations