© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 47403
    Prev
    Next
    INDEX
    Explanations

    or, can, may

    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
    Negative Logits
     tend
    -0.10
    大æ¦Ĥ
    -0.10
    大æ¦Ĥæĺ¯
    -0.10
     поможеÑĤ
    -0.09
    èĩ³å°ij
    -0.09
    èĤ¯å®ļä¼ļ
    -0.09
    å¿ħçĦ¶ä¼ļ
    -0.09
    å²±
    -0.09
    æģIJæĢķ
    -0.08
    åŁºæľ¬ä¸Ĭéĥ½
    -0.08
    POSITIVE LOGITS
    ä¹Łåı¯èĥ½
    0.21
    ä¸įä¸Ģå®ļ
    0.17
    ä¹Łåı¯ä»¥
    0.16
    æľªå¿ħ
    0.13
    å¾Īå·®
    0.13
    çĶļèĩ³æĺ¯
    0.11
    ä¹Łåı¯
    0.11
    å®ĥåı¯ä»¥
    0.10
    çĶļèĩ³
    0.10
    å®Įåħ¨åı¯ä»¥
    0.10
    Activations Density 0.293%

    No Known Activations