© 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. 2960
    Prev
    Next
    INDEX
    Explanations

    percentage of 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
    åĢĻ
    -0.09
    æľīå¤ļå°ij
    -0.09
     Continent
    -0.09
    è°¦
    -0.08
    æ¦ĤåĨµ
    -0.08
    ä¹Łåı¯ä»¥
    -0.08
    åĸĦæĦı
    -0.08
     Lehr
    -0.08
     Hem
    -0.08
    ç§ĺ
    -0.08
    POSITIVE LOGITS
    æķ´ä¸ª
    0.11
    æķ´ä½ĵ
    0.11
     overall
    0.11
    åħ¨éĥ¨
    0.11
     вÑģего
    0.10
     überhaupt
    0.10
    åĢĴ
    0.09
    åIJĪæ³ķæĢ§
    0.09
    ä¸ĢåĪĩ
    0.09
    overall
    0.09
    Activations Density 0.081%

    No Known Activations