© 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. 47472
    Prev
    Next
    INDEX
    Explanations

    is true

    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
     cand
    -0.10
     Cand
    -0.09
    mits
    -0.09
    zend
    -0.09
    ड
    -0.09
    åĮºåĨħ
    -0.08
    rest
    -0.08
    å¹³æĿ¿
    -0.08
    履约
    -0.08
    ç§ģãģĮ
    -0.08
    POSITIVE LOGITS
    æĥħåĨµ
    0.11
    ä¹Łæĺ¯å¦ĤæѤ
    0.10
     happens
    0.10
     happened
    0.10
     happen
    0.10
    çļĦæĦŁåıĹ
    0.09
    åıijçĶŁ
    0.09
    äºĭå®ŀ
    0.09
    çļĦæĥħåĨµ
    0.09
    èĿĩ
    0.09
    Activations Density 0.060%

    No Known Activations