© 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. 11945
    Prev
    Next
    INDEX
    Explanations

    military and defense organizations

    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
    æĪĸå¤ļ
    -0.10
    ç»Ĩç»Ĩ
    -0.10
    ÙĤاد
    -0.09
     Agent
    -0.09
    ione
    -0.08
    æĦıè§ģåıįé¦Ī
    -0.08
    究竣
    -0.08
    æ°¸ä¸į
    -0.08
    åĢļ
    -0.08
    wash
    -0.08
    POSITIVE LOGITS
    åĴĮ社ä¼ļ
    0.13
    æŀ¶
    0.09
    xon
    0.09
    æŁ°
    0.09
    ê¸Ī
    0.09
    è¯ł
    0.08
    å¿Ĵ
    0.08
    罩
    0.08
    awan
    0.08
     createState
    0.08
    Activations Density 0.007%

    No Known Activations