© 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. 18686
    Prev
    Next
    INDEX
    Explanations

    hot blood cells

    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
    usa
    -0.09
    -May
    -0.09
    um
    -0.08
    åĶ¿
    -0.08
    æľ¬å¸Ĥ
    -0.08
    dre
    -0.08
    alia
    -0.08
    eyer
    -0.08
    arious
    -0.08
    çķı
    -0.07
    POSITIVE LOGITS
    èµĦæºIJä¼ĺåĬ¿
    0.11
    ness
    0.10
    ï¸
    0.09
    åıįå¼¹
    0.09
    ä»·æł¼ä¸Ĭ涨
    0.09
    æĬķåħ¥åĪ°
    0.09
    ç«ŀäºīä¼ĺåĬ¿
    0.09
    é»ĺå¥ij
    0.09
    褰
    0.08
    æłı缮
    0.08
    Activations Density 0.003%

    No Known Activations