© 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. 33960
    Prev
    Next
    INDEX
    Explanations

    contractions ending in 't

    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
    ä¸įæĽ¾
    -0.11
    ä¸įåı¯
    -0.11
    æĪijä¸į
    -0.11
    ä¸įä½ı
    -0.10
    ä¸į足
    -0.10
    ä¸įä½Ĩ
    -0.10
    ä¸įæĺ¯å¾Ī
    -0.09
    ä¸įå±ŀäºİ
    -0.09
    ä¹ĭå¤ľ
    -0.09
     не
    -0.09
    POSITIVE LOGITS
    ä¸Ģä¸ĭåŃIJå°±
    0.10
    åıijçĶŁ
    0.10
    andi
    0.09
    theless
    0.09
    æľīä»»ä½ķ
    0.09
     há»ģ
    0.09
    epad
    0.09
    å½¢æĪIJ
    0.09
    æŀĦæĪIJ
    0.09
    ches
    0.09
    Activations Density 0.222%

    No Known Activations