© 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. 3391
    Prev
    Next
    INDEX
    Explanations

    government departments or agencies

    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
    éĺŁéķ¿
    -0.11
    裳
    -0.10
    å©Ĩå©Ĩ
    -0.10
    grounds
    -0.09
    å¸ģ
    -0.09
    ä¸Ńå¿ĥ主任
    -0.09
    ä¼Ļä¼´
    -0.08
    æĮĤéĴ©
    -0.08
    æIJŃæ¡£
    -0.08
    èĪªéģĵ
    -0.08
    POSITIVE LOGITS
    ç¢Į
    0.08
    åĸľ
    0.08
     facto
    0.08
    amic
    0.08
    ronic
    0.08
    ÑģÑĤеÑĢ
    0.08
    ATCH
    0.08
    ä¿Ŀå¯Ĩ
    0.08
    ways
    0.08
    .gov
    0.08
    Activations Density 0.012%

    No Known Activations