© 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. 59452
    Prev
    Next
    INDEX
    Explanations

    managed to

    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
    éļıåį³
    -0.09
    uality
    -0.09
    éļıä¹ĭ
    -0.09
    åħ·æľīä¸Ģå®ļ
    -0.09
    ÑĢÑĥÑĩ
    -0.08
    ä¸įåĬ¨
    -0.08
    以便
    -0.08
    ç«ŀäºīåĬĽ
    -0.08
    à¸Ļาà¸Ļ
    -0.08
    忽çĦ¶
    -0.08
    POSITIVE LOGITS
    æ²Ļåıij
    0.10
    è¦Ĩ
    0.10
    주ìĿĺ
    0.09
    éĢĥèĦ±
    0.09
    _drag
    0.09
    好å¤Ħ
    0.09
    说æľį
    0.09
    pire
    0.09
    æİĴæ¯Ĵ
    0.09
    ãģ¾ãģĦ
    0.09
    Activations Density 0.009%

    No Known Activations