© 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. 40134
    Prev
    Next
    INDEX
    Explanations

    with its

    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
    .Callback
    -0.09
    èħ¹éĥ¨
    -0.09
     Kensington
    -0.09
    สà¸Ļ
    -0.09
    åŃ½
    -0.09
    ãģĭãģ¤
    -0.09
    æ²±
    -0.09
    ниÑĩ
    -0.08
    apr
    -0.08
    ç°§
    -0.08
    POSITIVE LOGITS
    å®ĥçļĦ
    0.13
     its
    0.11
    åħ¶
    0.11
    çļĦåIJĦç§į
    0.11
    åIJĦç§į
    0.10
    åIJĦç§įåIJĦæł·
    0.10
     Its
    0.09
    ç§įç§į
    0.09
     Integrity
    0.09
    æ¶īåıĬåĪ°
    0.08
    Activations Density 0.040%

    No Known Activations