© 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. 26230
    Prev
    Next
    INDEX
    Explanations

    names after punctuation

    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
    贯穿
    -0.09
    .shtml
    -0.09
    èħ¾è®¯
    -0.09
     <--
    -0.08
    çŃĸ
    -0.08
    arkan
    -0.08
    è¦ĥ
    -0.08
    è§Ħç¨ĭ
    -0.07
    ÑIJ
    -0.07
     "+↵
    -0.07
    POSITIVE LOGITS
    é«ĺç´łè´¨
    0.09
    éĨĴäºĨ
    0.09
     اÙĦÙħÙĤدس
    0.09
    Localization
    0.08
    TN
    0.08
    çĶļ
    0.08
    ä¹ĥæĺ¯
    0.08
    theses
    0.08
    nore
    0.08
    .lazy
    0.08
    Activations Density 0.331%

    No Known Activations