© 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. 26115
    Prev
    Next
    INDEX
    Explanations

    given the same input

    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
     unb
    -0.09
     Lang
    -0.08
    æijħ
    -0.08
    ä½łå¥½
    -0.08
    äºĴåĬ©
    -0.08
    ä¸įå®Į
    -0.08
    éĢŁ
    -0.08
    ä¸įæĺİ
    -0.08
    esk
    -0.08
    æĬ±ä½ı
    -0.08
    POSITIVE LOGITS
    æijĨåľ¨
    0.11
    æŀ¶åŃIJ
    0.11
    åıªè¦ģæľī
    0.10
     пÑĢедоÑģÑĤавлен
    0.10
    abbo
    0.10
    æĮĩå¼ķ
    0.10
    æݥ触åĪ°
    0.09
    æĢĤ
    0.09
    ãĤĴä¸İãģĪ
    0.09
    ATAR
    0.09
    Activations Density 0.128%

    No Known Activations