© 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. 635
    Prev
    Next
    INDEX
    Explanations

    a/an followed by a noun

    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
    ä¸įæĪIJ
    -0.09
    _REGS
    -0.09
    æĬĢæľ¯çłĶåıij
    -0.08
     Shen
    -0.08
    _EOL
    -0.08
    عÙĦا
    -0.08
    åİ»è¿ĩ
    -0.08
     ÑģÑĢедне
    -0.08
    åħĨ
    -0.08
    agus
    -0.08
    POSITIVE LOGITS
    ä¸ĢæĹı
    0.11
    æĦŁè§ī
    0.11
    å®īåħ¨æĦŁ
    0.10
    åĤ¢
    0.10
     ability
    0.09
     need
    0.09
     sense
    0.09
     emphasis
    0.09
    emade
    0.09
    æľīæīĢ
    0.09
    Activations Density 0.197%

    No Known Activations