© 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. 50877
    Prev
    Next
    INDEX
    Explanations

    environmental contaminants and pesticides

    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
    æĿµ
    -0.10
    强åĪ¶
    -0.10
    prm
    -0.08
    左侧
    -0.08
    ä¸į解
    -0.08
     ÑģÑĤандаÑĢÑĤ
    -0.08
    ASIC
    -0.08
    pline
    -0.08
    ç¥ŀä»Ļ
    -0.08
     pedal
    -0.08
    POSITIVE LOGITS
    订
    0.09
    สะสม
    0.09
    èººåľ¨
    0.09
    é³ķ
    0.09
    æĭĴ
    0.09
    LOPT
    0.09
    è´¿
    0.08
     Moose
    0.08
    czy
    0.08
    ä¸įçŁ¥ä¸į
    0.08
    Activations Density 0.160%

    No Known Activations