© 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. 61092
    Prev
    Next
    INDEX
    Explanations

    called [noun]

    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
    pitch
    -0.10
    ä¿Ŀä¿®
    -0.09
    æľīä»»ä½ķ
    -0.09
    loadModel
    -0.09
     ÐijеÑģ
    -0.09
     Coupe
    -0.09
    è¶³å¤ŁçļĦ
    -0.09
     Paradise
    -0.08
    даÑĤÑĮ
    -0.08
    æŁ³
    -0.08
    POSITIVE LOGITS
    ä»Ģä¹Īåij¢
    0.14
    ç¼Ĺ
    0.09
    æĪijåľ¨
    0.09
    eka
    0.08
    æĪijæł¡
    0.08
     ``
    0.08
    éĺ¶æ®µæĢ§
    0.08
     “
    0.08
    åļ£
    0.08
    伫
    0.08
    Activations Density 0.066%

    No Known Activations