© 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. 39522
    Prev
    Next
    INDEX
    Explanations

    military deployment or assignment

    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
    æĸ°æĶ¿
    -0.09
    uru
    -0.09
    举起
    -0.08
    enheim
    -0.08
    vit
    -0.08
    æĺ¯ä¸Ģ件
    -0.08
    æīĵæĬĺ
    -0.08
    æĿ
    -0.08
    uada
    -0.08
    idi
    -0.08
    POSITIVE LOGITS
    éĥ¨ç½²
    0.13
    æ´¾éģ£
    0.13
    派驻
    0.11
    è¿ĻæĶ¯
    0.11
    éģ£
    0.11
    å°±è¿ij
    0.11
    ä¸ĢæĶ¯
    0.11
    åĤ¨å¤ĩ
    0.11
    çĶ¨äºİ
    0.10
    éĺŁä¼į
    0.10
    Activations Density 0.103%

    No Known Activations