© 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. 3938
    Prev
    Next
    INDEX
    Explanations

    military operations and command structures

    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
    äº²çľ¼
    -0.09
    ioc
    -0.09
    nos
    -0.09
    ToSelector
    -0.09
    PHA
    -0.09
    åĨ¥
    -0.09
    驺
    -0.08
    éģĩ
    -0.08
    hands
    -0.08
    arro
    -0.08
    POSITIVE LOGITS
    æŀ¢
    0.09
    ç¾°
    0.09
    æĪĺçķ¥
    0.09
    æĪĺçķ¥æĢ§
    0.09
    åĨ³æĪĺ
    0.09
     operations
    0.09
    ä¿Ŀ湿
    0.09
    ë²Į
    0.08
    æĦıè§ģ建议
    0.08
    ä»°
    0.08
    Activations Density 0.143%

    No Known Activations