© 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. 5955
    Prev
    Next
    INDEX
    Explanations

    not necessarily

    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
    åŁºæľ¬ä¸Ĭ
    -0.10
    æģIJæĢķ
    -0.10
    åĦ¿
    -0.09
    uez
    -0.09
    èĩ³å°ij
    -0.09
    åĩłä¹İ
    -0.08
    almost
    -0.08
    ohl
    -0.08
    å°½éĩı
    -0.08
    éĢļ常
    -0.08
    POSITIVE LOGITS
    æĦıä¹īä¸ĬçļĦ
    0.11
    好äºĭ
    0.10
    å°±æѤ
    0.10
    马ä¸Ĭå°±
    0.10
     necessarily
    0.10
    æıIJä¾Ľä¼ĺè´¨
    0.09
    æĭ¿æĿ¥
    0.09
    建ç«ĭèµ·
    0.09
    åĿıäºĭ
    0.09
    åĽłä¸ºä»ĸ
    0.09
    Activations Density 0.018%

    No Known Activations