© 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. 60783
    Prev
    Next
    INDEX
    Explanations

    of properties, differential, ideas, individual

    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
    社ä¼ļç»Ħç»ĩ
    -0.11
    å°ī
    -0.09
    æĹłæ¯Ķ
    -0.09
    s
    -0.09
    æ¯ı次éĥ½
    -0.09
    æ¯ı次
    -0.09
    å§Ĭ妹
    -0.08
    æŁł
    -0.08
    èµ£
    -0.08
    é¢ijé¢ij
    -0.08
    POSITIVE LOGITS
    _crypto
    0.09
    ÑĨов
    0.09
    anch
    0.09
    åģıä½İ
    0.09
    uD
    0.08
    omid
    0.08
     Ðijо
    0.08
    ¦
    0.08
    .publisher
    0.08
    iazza
    0.08
    Activations Density 0.192%

    No Known Activations