© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9401
    Prev
    Next
    INDEX
    Explanations

    naive, untested, inexperienced

    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
    ä¸įä¸ĭ
    -0.10
    æģª
    -0.10
    è§īæĤŁ
    -0.09
    æĽ·
    -0.09
    ero
    -0.09
    омеÑĢ
    -0.09
    æ¯ĴæĢ§
    -0.08
    è·ijäºĨ
    -0.08
    kah
    -0.08
    THR
    -0.08
    POSITIVE LOGITS
    é¦ĸ次
    0.15
    éĻĮçĶŁ
    0.15
    æľªæĽ¾
    0.14
    ç»ıéªĮ
    0.14
    ä»İæľª
    0.14
    åĪĿ次
    0.13
    没è§ģè¿ĩ
    0.13
    ä»İæĿ¥æ²¡
    0.12
    æ¬łç¼º
    0.12
    çļĦç»ıéªĮ
    0.12
    Activations Density 0.117%

    No Known Activations