© 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. 6120
    Prev
    Next
    INDEX
    Explanations

    Indian film titles

    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
    lette
    -0.10
    éĿ©
    -0.09
    åľ°äº§
    -0.09
    몰
    -0.09
    ä¹ĭéģĵ
    -0.09
    Ùħر
    -0.08
    ÑĢÑı
    -0.08
    çľ¼è§Ĵ
    -0.08
    ogle
    -0.08
    ä¸įäºĨ
    -0.08
    POSITIVE LOGITS
    วย
    0.09
     Anc
    0.08
    豪åįİ
    0.08
    æĦŁåºĶ
    0.08
    åįĩåѦ
    0.08
     grand
    0.08
    grand
    0.08
    æĿ¥åĽŀ
    0.08
    alli
    0.07
    æĶ¯æĴij
    0.07
    Activations Density 0.351%

    No Known Activations