© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19523
    Prev
    Next
    INDEX
    Explanations

    immune to

    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
    ä¼Łå¤§
    -0.08
    æij¸
    -0.08
    çĬĬ
    -0.08
    寡
    -0.08
    管
    -0.08
    éĩĬæĶ¾
    -0.08
    allah
    -0.08
    æĶ»åĬ¿
    -0.08
     обÑıзан
    -0.08
    大å¦Ī
    -0.08
    POSITIVE LOGITS
    åıijçĶŁåľ¨
    0.12
    身边
    0.10
    并ä¸į代表
    0.10
    ä¸įçĽ¸ä¿¡
    0.10
    åıijçĶŁçļĦ
    0.10
    Occurs
    0.09
    azar
    0.09
    身边çļĦ
    0.09
    ingly
    0.09
    ackage
    0.09
    Activations Density 0.064%

    No Known Activations