© 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. 60693
    Prev
    Next
    INDEX
    Explanations

    disillusioned, cynical, relativism

    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
    æĿ³
    -0.11
    ancel
    -0.09
    æĥ³åĥı
    -0.09
     Cedar
    -0.08
    ãģĨ
    -0.08
     اÙĦسÙĨØ©
    -0.08
    NER
    -0.08
    ings
    -0.08
     Surprise
    -0.08
    èł¢
    -0.08
    POSITIVE LOGITS
     cynical
    0.14
     cyn
    0.12
    é¢ĵ
    0.10
    ä¸įçĽ¸ä¿¡
    0.10
    æĤ²è§Ĥ
    0.10
    ä¸ĩäºĭ
    0.09
    ä¸ĢåĪĩéĥ½
    0.09
     pessim
    0.09
    å½Ĵ纳
    0.09
    ç¨Ķ
    0.09
    Activations Density 0.023%

    No Known Activations