© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8928
    Prev
    Next
    INDEX
    Explanations

    getting things done

    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
    Not in Any Lists

    No Comments

    Negative Logits
    éħįå¥Ĺ设æĸ½
    -0.10
    æĸij
    -0.09
    ç§ijæĬĢ大åѦ
    -0.08
     ÃŃch
    -0.08
    bie
    -0.08
    è®°è½½
    -0.08
    apas
    -0.08
    gest
    -0.08
    éĸĴ
    -0.08
    çļĦåĪ©çĽĬ
    -0.08
    POSITIVE LOGITS
    亲
    0.10
    .slim
    0.10
    亲è¿ij
    0.09
    chluss
    0.09
    rum
    0.09
     ÑĢаздел
    0.09
     AUTHOR
    0.08
    .setAction
    0.08
    åıĪæĺ¯
    0.08
    ycin
    0.08
    Activations Density 0.050%

    No Known Activations