© 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. 63900
    Prev
    Next
    INDEX
    Explanations

    victims and victimization

    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
    eg
    -0.10
    è¿Ļä½į
    -0.10
    aha
    -0.09
    æĢ»èĢĮè¨Ģä¹ĭ
    -0.09
    ons
    -0.09
    è¿¥
    -0.09
    ings
    -0.08
    ãģŁãģı
    -0.08
    vin
    -0.08
    inqu
    -0.08
    POSITIVE LOGITS
    iveness
    0.12
    ç²¾ç¥ŀ
    0.08
    IRS
    0.08
    naire
    0.08
    éĺŁä¼į建设
    0.08
    udge
    0.08
     té
    0.08
    âĤ¬âĦ¢
    0.08
    opia
    0.08
    å¨ĺå¨ĺ
    0.08
    Activations Density 0.012%

    No Known Activations