© 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. 54464
    Prev
    Next
    INDEX
    Explanations

    official links and resource pages

    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
    å¿ĺ
    -0.10
    ä¹±
    -0.09
    ä¸Ģå°ģ
    -0.09
    èĢģåŃIJ
    -0.09
    ä¸Ģç¬ij
    -0.09
     Lol
    -0.09
    кÑģ
    -0.08
    .jpg
    -0.08
    å¿ĺè®°
    -0.08
     Honor
    -0.08
    POSITIVE LOGITS
    ä¸İæѤ
    0.10
    å®ĥ们
    0.10
    æĪĸå°Ĩ
    0.10
     пÑĢоб
    0.09
    ãĤīãĤĮãģ¦ãģĦãĤĭ
    0.09
    ä½¥
    0.09
    ç¾½
    0.09
    anden
    0.09
    ç»Ŀ对ä¸įä¼ļ
    0.09
    è¿ĻäºĽéĹ®é¢ĺ
    0.09
    Activations Density 0.089%

    No Known Activations