© 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. 40194
    Prev
    Next
    INDEX
    Explanations

    personal opinion or perception

    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
    æĪĸå°Ĩ
    -0.13
    对该
    -0.10
    ennen
    -0.10
    æĺİåªļ
    -0.10
    æīĵéĢļ
    -0.10
    对æѤ
    -0.10
     اÙĦعÙħ
    -0.10
    æµ·éĩı
    -0.09
    æĦģ
    -0.09
    ä¸įè§ģäºĨ
    -0.09
    POSITIVE LOGITS
    ãģŁãĤī
    0.09
    ocket
    0.08
    ients
    0.08
    yme
    0.08
    çĽijçIJĨ
    0.08
     personally
    0.07
    ej
    0.07
    ayne
    0.07
     Garrett
    0.07
     Swiss
    0.07
    Activations Density 0.024%

    No Known Activations