© 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. 35057
    Prev
    Next
    INDEX
    Explanations

    pick from lists

    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
    伶
    -0.11
    иж
    -0.09
    æľī大éĩıçļĦ
    -0.08
    ãĥ§
    -0.08
    å²Ń
    -0.08
     ÐłÐ¾Ñģ
    -0.08
    é¢ij
    -0.08
    åįĩé«ĺ
    -0.08
    为é¦ĸçļĦ
    -0.08
     Burr
    -0.08
    POSITIVE LOGITS
    å®ĥ们
    0.11
    æ¯ķç«Ł
    0.10
    ä¸įçĦ¶
    0.10
    å®ĥ
    0.10
    è¦ģçŁ¥éģĵ
    0.09
    è¿Ļä¹Łæĺ¯
    0.09
    ãģªãģıãģ¦
    0.09
    åIJ¦åĪĻ
    0.08
    çķ¢ç«Ł
    0.08
    å®ĥæĺ¯
    0.08
    Activations Density 0.376%

    No Known Activations