© 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. 11076
    Prev
    Next
    INDEX
    Explanations

    affect, influence, contribute

    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
    åħij
    -0.09
    ä¹Łæĺ¯ä¸Ģç§į
    -0.09
    éĿ¢ä¸´çļĦ
    -0.09
    incer
    -0.09
    ä¼´éļı
    -0.09
    è¶Ĭ
    -0.09
    iration
    -0.09
    交éĢļæŀ¢çº½
    -0.08
     Moff
    -0.08
    大楼
    -0.08
    POSITIVE LOGITS
    åĽłç´ł
    0.10
     Hd
    0.09
    顺
    0.09
    æĽ²æĬĺ
    0.08
    OWN
    0.08
    HD
    0.08
    æĪijæĬĬ
    0.08
     доп
    0.08
    gar
    0.08
    unn
    0.08
    Activations Density 0.239%

    No Known Activations