© 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. 24182
    Prev
    Next
    INDEX
    Explanations

    numbers and relative order

    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
    çļĦãģ«ãģ¯
    -0.10
     Cout
    -0.08
    æĺ¯ä¸Ģç§į
    -0.08
    niest
    -0.08
    едÑĮ
    -0.08
    !--
    -0.08
    %C
    -0.08
    å½ĵåľ°äºº
    -0.07
     Rath
    -0.07
    cole
    -0.07
    POSITIVE LOGITS
    çŃĶåį·
    0.10
    izations
    0.10
    éĿ¢åŃĶ
    0.10
    ä¼ĹæīĢ
    0.09
    ами
    0.09
    aus
    0.09
    è·Įå¹ħ
    0.09
    æĤ¨çļĦåŃ©åŃIJ
    0.09
    ä¹ĭæĹħ
    0.09
    åħŃåIJĪ
    0.09
    Activations Density 3.400%

    No Known Activations