© 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. 58135
    Prev
    Next
    INDEX
    Explanations

    Spanish definite articles followed by 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
    æľīä¿¡å¿ĥ
    -0.09
     Hass
    -0.08
    è¿Ļç±»
    -0.08
    го
    -0.08
    orn
    -0.08
    inus
    -0.08
    çĶļèĩ³æĺ¯
    -0.08
    acular
    -0.08
    驳
    -0.08
    Certificates
    -0.08
    POSITIVE LOGITS
    ENA
    0.11
    åĪĹ车
    0.10
    çĻ½èī²çļĦ
    0.10
    鼶åĶ®
    0.09
     infl
    0.09
    æĺİå¹´
    0.09
    çĶŁæ´»çļĦ
    0.09
    âĨķ
    0.09
    æ´»çĿĢ
    0.09
    ï¸
    0.09
    Activations Density 0.037%

    No Known Activations