© 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. 3272
    Prev
    Next
    INDEX
    Explanations

    full version free download

    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
     вообÑīе
    -0.09
    atan
    -0.08
    pid
    -0.07
     nap
    -0.07
    é«ĺåĩº
    -0.07
    ãģĤãģ£ãģŁ
    -0.07
     Blogs
    -0.07
    (Convert
    -0.07
    æłı
    -0.07
    onis
    -0.07
    POSITIVE LOGITS
    交ç»Ļ
    0.09
    æĺ¯éĿŀ
    0.09
    çīĪ
    0.09
    æĪĸå¤ļ
    0.09
    â»
    0.09
    ãĤ¹ãĤ¿
    0.09
    ä¸Ģ次æĢ§
    0.09
    даÑĤÑĮ
    0.09
    è¿ijåĩłå¹´
    0.08
    æĨĶ
    0.08
    Activations Density 0.014%

    No Known Activations