© 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. 32860
    Prev
    Next
    INDEX
    Explanations

    the expectation or result

    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
    éĤ£æĺ¯
    -0.12
    ç¬Ļ
    -0.10
    ä½Ĩä¸įéĻIJäºİ
    -0.10
    å©Ĩ
    -0.09
    ãģĿãĤĮãģ¯
    -0.09
    æĽľ
    -0.09
    гÑĢан
    -0.09
    åķĨä¼ļ
    -0.08
     con
    -0.08
    ãĢįãĢĮ
    -0.08
    POSITIVE LOGITS
    orem
    0.11
    åIJĮæł·
    0.11
    åı¦ä¸Ģæĸ¹éĿ¢
    0.11
    åIJĮæł·çļĦ
    0.10
    注æĦıåĪ°
    0.10
    ä¸įä»ħå¦ĤæѤ
    0.10
    æľīä¸ĢçĤ¹
    0.09
    åĢ¼å¾Ĺä¸ĢæıIJ
    0.09
    åĢ¼å¾Ĺ注æĦı
    0.09
    è°ĪåĪ°
    0.09
    Activations Density 0.268%

    No Known Activations