© 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. 9972
    Prev
    Next
    INDEX
    Explanations

    heard someone or something

    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
    atsby
    -0.10
    elines
    -0.09
    enheim
    -0.09
    伸åĩº
    -0.09
    ari
    -0.09
    cona
    -0.09
    eurs
    -0.08
    onte
    -0.08
    ä¼Ļ
    -0.08
    ä½İ头
    -0.08
    POSITIVE LOGITS
    ä¸ĢåIJ¬
    0.13
    lessly
    0.10
    æľī人说
    0.10
    /watch
    0.10
     rÃłng
    0.09
    allis
    0.09
    æĿ¥èĩª
    0.09
    é¹Ħ
    0.09
    kening
    0.09
    åIJ¬è§ģ
    0.08
    Activations Density 0.023%

    No Known Activations