© 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. 32572
    Prev
    Next
    INDEX
    Explanations

    missiles, defense, air, mobile

    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
    ersive
    -0.10
    ç²ī
    -0.09
    æīĵçĿĢ
    -0.09
    è¾ĵç»Ļ
    -0.08
    èĪª
    -0.08
    è¾ĵ
    -0.08
     acknowledgement
    -0.08
    åĽ¢ç»ĵ
    -0.08
    porte
    -0.08
    æ³¾
    -0.08
    POSITIVE LOGITS
    å¨ģæħij
    0.10
    åŁİå¸Ĥ群
    0.09
    åĬ¾
    0.09
    åı¯éĿłçļĦ
    0.09
    å¼ĢæĶ¯
    0.09
    logan
    0.09
    导弹
    0.08
    æµģæ°ĵ
    0.08
    éĺ²å¾¡
    0.08
    å°ıä¼Ļä¼´
    0.08
    Activations Density 0.057%

    No Known Activations