© 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. 18458
    Prev
    Next
    INDEX
    Explanations

    customs code, export, duty

    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
    ripp
    -0.10
    è¾ĺ
    -0.09
    ç»ıå¼Ģ
    -0.09
    å¥łåŁº
    -0.09
    åŁºå±Ĥ
    -0.09
    rick
    -0.09
    AVA
    -0.09
    æģ¯
    -0.09
    è¦ĨçĽĸçİĩ
    -0.08
    潦
    -0.08
    POSITIVE LOGITS
    ä¿Ŀç¨İ
    0.12
    æµ·åħ³
    0.12
    éĢļåħ³
    0.10
    è´§çī©
    0.10
    å®ŀçī©
    0.10
     inbound
    0.09
    ç¼ī
    0.09
    å®ŀæĸ½
    0.09
     ENC
    0.09
    åħįç¨İ
    0.09
    Activations Density 0.041%

    No Known Activations