© 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. 61095
    Prev
    Next
    INDEX
    Explanations

    year by year

    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
     ÐijолÑĮÑĪ
    -0.10
    麾
    -0.09
    çļĦä¸Ģç§į
    -0.09
    æĹłè§Ĩ
    -0.09
    èıĬ
    -0.09
    浦
    -0.09
    ense
    -0.09
    åIJĮæľŁ
    -0.09
    æ¸Ĭ
    -0.08
    æĭĽ
    -0.08
    POSITIVE LOGITS
    ãĢħ
    0.14
    ë§Īëĭ¤
    0.13
    ä¸įå°ij
    0.11
    ä¸Ģ次次
    0.11
    è¶ĬæĿ¥è¶Ĭå¤ļ
    0.10
    屡
    0.09
    æİ¥çĿĢ
    0.09
    utex
    0.09
    ä¸Ģä¸Ģ
    0.09
    æİ¥èijĹ
    0.09
    Activations Density 0.030%

    No Known Activations