© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51014
    Prev
    Next
    INDEX
    Explanations

    if example

    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
    好象
    -0.09
    asco
    -0.09
    ment
    -0.09
    uset
    -0.09
    åĩłä¹İæĺ¯
    -0.08
    ä¸įåı¯æĢĿè®®
    -0.08
    æį®è¯´
    -0.08
    å¼Ĥ常
    -0.08
    æĩĤäºĭ
    -0.08
    为空
    -0.08
    POSITIVE LOGITS
    æŁIJ
    0.15
    æŁIJä¸Ģ
    0.14
    æŁIJ个
    0.13
    æ¯Ķå¦Ĥ说
    0.11
     someday
    0.10
    æľīä¸Ģä½į
    0.10
    åıªçŁ¥éģĵ
    0.09
    someone
    0.09
    pag
    0.09
     нек
    0.09
    Activations Density 0.474%

    No Known Activations