© 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. 62764
    Prev
    Next
    INDEX
    Explanations

    social events and parties

    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
     niên
    -0.09
     Tri
    -0.08
    å¹´æĿ¥
    -0.08
    åĿĽ
    -0.08
    åħħå½ĵ
    -0.08
    camp
    -0.08
     camp
    -0.08
    ORK
    -0.08
    acts
    -0.07
    erna
    -0.07
    POSITIVE LOGITS
    åĿļ
    0.09
     Harmon
    0.09
    çķĢ
    0.09
    è¿ĻåIJį
    0.09
    ÑģÑĤо
    0.09
    phant
    0.09
    æį®æĬ¥éģĵ
    0.09
    innacle
    0.09
     гаÑĢ
    0.09
    zier
    0.09
    Activations Density 0.012%

    No Known Activations