© 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. 47661
    Prev
    Next
    INDEX
    Explanations

    Texas, Cup, anth

    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
    éķ¿æķĪ
    -0.09
    ä»ĬåIJİ
    -0.09
    pus
    -0.09
    NullOr
    -0.09
    otron
    -0.08
    ÑĤеÑĢ
    -0.08
    AuthToken
    -0.08
    kits
    -0.08
    çĭł
    -0.08
     Hunts
    -0.08
    POSITIVE LOGITS
    Drv
    0.09
    Õ»
    0.09
    èł¹
    0.09
    è·ª
    0.08
    TÃľ
    0.08
    vd
    0.08
    odia
    0.08
    ä»Ĺ
    0.08
    æĿĸ
    0.08
    ãģ¨ãģĦãģĨãģ®ãģĮ
    0.08
    Activations Density 0.021%

    No Known Activations