© 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. 928
    Prev
    Next
    INDEX
    Explanations

    seemed to

    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
    æ¸ħæ·¡
    -0.11
    平淡
    -0.10
    éĿ¢åŃIJ
    -0.09
    ãģĤãĤĬãģĮ
    -0.08
     thượng
    -0.08
    ä½ķåĨµ
    -0.08
    丰ç¡ķ
    -0.08
    æĥ¯
    -0.08
    .sk
    -0.08
     beh
    -0.08
    POSITIVE LOGITS
    æľīç§į
    0.11
    æľīæĦı
    0.09
    zm
    0.09
    èĩªåıij
    0.09
    ä¸Ģåī¯
    0.09
    ä¸ĵä¸ļçŁ¥è¯Ĩ
    0.09
    èĮĨ
    0.09
    çħŀ
    0.09
    æįį
    0.09
    åħ³å¿ĥ
    0.09
    Activations Density 0.035%

    No Known Activations