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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 39526
    Prev
    Next
    INDEX
    Explanations

    national and European contexts

    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
    åħ¨çIJĥ
    -0.12
    éĶ£
    -0.10
    auc
    -0.09
     миÑĢов
    -0.09
    åħ¨æµģç¨ĭ
    -0.09
    ä¸ĸçķĮåIJĦåĽ½
    -0.09
     auc
    -0.09
     global
    -0.09
     worldwide
    -0.08
     globally
    -0.08
    POSITIVE LOGITS
    atee
    0.10
    夯å®ŀ
    0.10
    éĢĹ
    0.09
    æĹ·
    0.08
    éĻ¶
    0.08
    åѤåįķ
    0.08
    çİ®
    0.08
     Elf
    0.08
    äº¤æĽ¿
    0.08
     Contrib
    0.08
    Activations Density 0.151%

    No Known Activations