© 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. 30354
    Prev
    Next
    INDEX
    Explanations

    environmental pollutants and exposure

    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
     Svens
    -0.10
    ä¸įåľ¨
    -0.10
    è¾ķ
    -0.10
    ì§ĵ
    -0.10
    ä¼łåĩº
    -0.09
    CellStyle
    -0.09
    åıĹ访
    -0.09
    æ¦ij
    -0.09
    ло
    -0.09
    çŃı
    -0.08
    POSITIVE LOGITS
     expos
    0.10
    æļ´éľ²
    0.10
     exposure
    0.10
    çݯå¢ĥ
    0.09
    æĺ¯æĪij们
    0.09
    汽车
    0.09
     Exposure
    0.09
    è¡Ĺéģĵ
    0.09
    éĥ½å¸Ĥ
    0.09
     urban
    0.09
    Activations Density 0.258%

    No Known Activations