© 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. 2009
    Prev
    Next
    INDEX
    Explanations

    examples of inclusion

    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
    æİ¥çĿĢ
    -0.11
    çŀ¿
    -0.10
    ibrator
    -0.09
    ä¹Łå°±æĺ¯è¯´
    -0.09
    ä¸įçķĻ
    -0.09
    è¿ĺ
    -0.09
     either
    -0.09
    Ñĥд
    -0.09
     Either
    -0.09
    è¯Ŀ说
    -0.09
    POSITIVE LOGITS
    ä½Ĩä¸įéĻIJäºİ
    0.19
    æĪijèĩªå·±
    0.12
     ones
    0.11
    wise
    0.10
     notably
    0.10
    æĪij个人
    0.09
    åľ¨æĪij
    0.09
     those
    0.09
    åľ¨åĨħçļĦ
    0.09
     myself
    0.09
    Activations Density 0.045%

    No Known Activations