© 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. 32738
    Prev
    Next
    INDEX
    Explanations

    oxygen partial pressure

    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
    å¤§åĽ½
    -0.09
    arkin
    -0.08
    å®Ŀè´Ŀ
    -0.08
    ä¸įçĦ¶
    -0.08
    åķ¬
    -0.08
     бÑĥкв
    -0.08
    大大å°ı
    -0.08
    éĶį
    -0.08
    æݾ
    -0.07
    tog
    -0.07
    POSITIVE LOGITS
    çŃ¹
    0.09
    ä¸įå®ľ
    0.07
    é¢IJ
    0.07
    ç±Į
    0.07
    esa
    0.07
    eden
    0.07
    æĮĤçīĮ
    0.07
    对åħ¶
    0.06
     presumably
    0.06
    озд
    0.06
    Activations Density 10.849%

    No Known Activations