© 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. 23672
    Prev
    Next
    INDEX
    Explanations

    after all

    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
    çļĦéĤ£ç§į
    -0.11
    æĤ²åĵĢ
    -0.10
    åķĥ
    -0.09
    å¾·èĤ²
    -0.09
    Sus
    -0.09
    课å¤ĸ
    -0.09
    éĿŀ常好çļĦ
    -0.09
    è¯
    -0.09
    éĤ£ç§į
    -0.09
    åį»
    -0.09
    POSITIVE LOGITS
    æ¯ķç«Ł
    0.19
    çķ¢ç«Ł
    0.14
    æ¯ķç«Łæĺ¯
    0.14
     ведÑĮ
    0.11
     ÐĴедÑĮ
    0.10
    è¿Ļæł·æīįèĥ½
    0.09
     przecież
    0.09
    æĹ¢è¦ģ
    0.08
    åľ¨ä¸Ģ个
    0.08
    è§Į
    0.08
    Activations Density 0.008%

    No Known Activations