© 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. 47625
    Prev
    Next
    INDEX
    Explanations

    program is free

    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
    é£ŀæī¬
    -0.09
    .mybatis
    -0.09
    ä½İä½į
    -0.09
    redni
    -0.09
    inds
    -0.09
    èħ¾
    -0.09
    eness
    -0.09
    çİ©åħ·
    -0.08
    æ·Ģ
    -0.08
    -preview
    -0.08
    POSITIVE LOGITS
     programs
    0.17
    (program
    0.16
    program
    0.16
    programs
    0.16
     program
    0.15
     Programs
    0.15
    .program
    0.15
    (Program
    0.15
     programa
    0.15
    ãĥĹãĥŃãĤ°ãĥ©ãĥł
    0.14
    Activations Density 0.139%

    No Known Activations