© 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. 57880
    Prev
    Next
    INDEX
    Explanations

    exclamations of surprise or strong emotion

    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
    大æĸ¹
    -0.10
    udeau
    -0.10
    æĺİæľĹ
    -0.09
    zech
    -0.09
    urred
    -0.09
     дело
    -0.09
    åĪĿå¿ĥ
    -0.09
    illé
    -0.08
    clusive
    -0.08
    orners
    -0.08
    POSITIVE LOGITS
    æĭħå¿ĥ
    0.09
    æĪ¬
    0.09
    ç«Ł
    0.08
    禽
    0.08
    å®ĥæĺ¯
    0.08
    vir
    0.08
    ä¸įçĦ¶
    0.08
     ÑĦакÑĤ
    0.08
    ening
    0.08
    unte
    0.08
    Activations Density 0.013%

    No Known Activations