© 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. 4086
    Prev
    Next
    INDEX
    Explanations

    you or thee followed by text

    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
    å¢Ģ
    -0.10
    ITTER
    -0.10
    icle
    -0.08
     пеÑĩ
    -0.08
    аÑĩ
    -0.08
    履约
    -0.08
    çķı
    -0.08
    YST
    -0.08
    æĤ¨åı¯ä»¥
    -0.08
     Klopp
    -0.08
    POSITIVE LOGITS
    æ¿ł
    0.10
    ä¼¼çļĦ
    0.08
    (::
    0.08
    ãĤ·ãĥªãĥ¼ãĤº
    0.08
    大åħ¨
    0.08
    ç³»åĪĹ
    0.08
    ARB
    0.08
     décid
    0.08
    oks
    0.08
     mừng
    0.08
    Activations Density 0.046%

    No Known Activations