© 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. 27597
    Prev
    Next
    INDEX
    Explanations

    is a/called/associated/believed

    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
    olk
    -0.09
    æīª
    -0.08
    åĴĮå°ļ
    -0.08
    èµ°åĩº
    -0.08
    æĹ¥æĬ¥
    -0.08
    ksam
    -0.08
     salsa
    -0.08
    æīĭæĦŁ
    -0.08
    çļĦæľºä¼ļ
    -0.07
    åļ¼
    -0.07
    POSITIVE LOGITS
    çĶŁèĤ²
    0.10
    ipc
    0.10
    æīĭæĮģ
    0.09
    æĪijä»¬çŁ¥éģĵ
    0.09
    .toObject
    0.09
    让人们
    0.09
    形象
    0.09
    èµIJ
    0.09
    _dataframe
    0.09
    çļĦ形象
    0.09
    Activations Density 0.088%

    No Known Activations