© 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. 12423
    Prev
    Next
    INDEX
    Explanations

    expressions of sympathy or opinion

    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
    èħ¥
    -0.11
    èĢĮçİ°åľ¨
    -0.10
    пл
    -0.09
    .Framework
    -0.09
    _UNDEF
    -0.09
    ucer
    -0.09
    åŁĭ
    -0.09
    åĬ¨æĦŁ
    -0.09
    uers
    -0.09
    undef
    -0.09
    POSITIVE LOGITS
    anz
    0.11
    ANC
    0.09
    ÙĬÙĩ
    0.08
    åĴĮæĶ¯æĮģ
    0.08
    ant
    0.08
     Bauer
    0.08
    ä¸ĩåĪĨ
    0.08
     GIF
    0.08
    éĢģç»Ļ
    0.08
    ç¢ľ
    0.08
    Activations Density 0.003%

    No Known Activations