© 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. 49790
    Prev
    Next
    INDEX
    Explanations

    begging or pleading for something

    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
    ife
    -0.09
    å®ļäºĨ
    -0.09
    å¾Īæľī
    -0.08
    ç´§åĩij
    -0.08
     bufio
    -0.08
     Beste
    -0.08
    ä¸įéĹ´
    -0.08
    ган
    -0.08
    åĸľ
    -0.08
    èĽī
    -0.07
    POSITIVE LOGITS
    è¡·
    0.10
    ingly
    0.10
    缨
    0.09
    unte
    0.09
    ä¸įå·²
    0.09
    fully
    0.09
    ssé
    0.09
    æģ³
    0.09
    çļĦå±ĢéĿ¢
    0.09
    çݰ身
    0.09
    Activations Density 0.013%

    No Known Activations