© 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. 16645
    Prev
    Next
    INDEX
    Explanations

    apply or applying

    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
    人å¿ĥ
    -0.09
     ÑģовеÑĢ
    -0.09
    implemented
    -0.09
    æĬĵ
    -0.09
    Prototype
    -0.09
     Localization
    -0.08
    обÑīе
    -0.08
    æĿ¯åŃIJ
    -0.08
    orama
    -0.08
    ТÐĺ
    -0.08
    POSITIVE LOGITS
    æĸ½
    0.11
     apply
    0.11
     brakes
    0.11
    çļĦåİŁåĪĻ
    0.11
     applies
    0.11
    apply
    0.11
    .apply
    0.10
    è¿Ļç§įæĸ¹æ³ķ
    0.10
     Apply
    0.10
     applying
    0.09
    Activations Density 0.124%

    No Known Activations