© 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. 62359
    Prev
    Next
    INDEX
    Explanations

    units followed by of or in

    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
    毫
    -0.09
    éĨª
    -0.09
    رات
    -0.09
    éĹ¨æ§Ľ
    -0.09
    磾
    -0.08
    Glass
    -0.08
     اÙĦÙĪØŃ
    -0.08
    ä¿Ŀå¯Ĩ
    -0.08
    Ñĥй
    -0.08
    èĤĭ
    -0.08
    POSITIVE LOGITS
    à¸Ĥà¸Ńà¸ĩà¸ģาร
    0.12
     of
    0.10
    åĹª
    0.08
    èĪ¬çļĦ
    0.08
    éģij
    0.08
    åľ¨åĨħçļĦ
    0.08
    导读
    0.08
    ä¹ĭæĥħ
    0.08
    çļĦ游æĪı
    0.08
    çļĦåľ°åĽ¾
    0.08
    Activations Density 0.058%

    No Known Activations