© 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. 7900
    Prev
    Next
    INDEX
    Explanations

    specified user, of the

    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
    è¿ĻçĤ¹
    -0.09
    coon
    -0.08
    ãģ©ãģĵãĤį
    -0.08
    ÑģÑĢ
    -0.08
    顶å°ĸ
    -0.08
    é«ĺè¾¾
    -0.08
    åıĮåıĮ
    -0.08
    åįģæĿ¡
    -0.08
    ë¬ĺ
    -0.08
    çĽĴåŃIJ
    -0.08
    POSITIVE LOGITS
    èĩ³å°ij
    0.11
    该éĻ¢
    0.10
     said
    0.08
    è¯Ŀ说
    0.08
    âĦ¢
    0.08
    .toLocale
    0.08
    toLocale
    0.08
    lect
    0.08
    æ¯Ķäºļ
    0.08
    åĴ¨
    0.08
    Activations Density 0.672%

    No Known Activations