© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 22300
    Prev
    Next
    INDEX
    Explanations

    such a

    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
    æł·åŃIJ
    -0.11
    éĤ£ç§į
    -0.10
    çļĦéĤ£ä¸Ģ
    -0.09
    æľīä¸Ģç§į
    -0.09
    è¿Ļ两ç§į
    -0.09
    éĤ£ä¸Ģ
    -0.09
    è¿Ļ个è¯į
    -0.09
    éĤ£ä¸ª
    -0.09
    è¿Ļç§įæĸ¹æ³ķ
    -0.09
    çĭ¬ä¸Ģ
    -0.09
    POSITIVE LOGITS
    è¿ĻèĪ¬
    0.12
    ils
    0.10
    æīįä¼ļ
    0.09
    æĪijä»¬ä¹Ł
    0.09
     Becker
    0.09
    IEL
    0.09
    å±Ĥåĩºä¸įç©·
    0.08
    庶
    0.08
     Nab
    0.08
    æīįåı¯ä»¥
    0.08
    Activations Density 0.116%

    No Known Activations